© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 49307
    Prev
    Next
    INDEX
    Explanations

    general writing

    np_max-act · gemini-2.0-flash

    user directives to produce or summarize structured technical content (e.g., plans/specifications), especially ISO 26262-style requirements.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flakes
    -0.08
    /news
    -0.07
    .slide
    -0.07
    .mat
    -0.07
     think
    -0.07
    .se
    -0.07
    ETHOD
    -0.07
    .shape
    -0.07
    -learning
    -0.07
    /math
    -0.06
    POSITIVE LOGITS
     TLabel
    0.07
     Connectivity
    0.07
    ಐ
    0.07
    造成
    0.06
     côt
    0.06
    ı
    0.06
    %
↵
    0.06
    仅
    0.06
    _Destroy
    0.06
    AILS
    0.06
    Activations Density 0.821%

    No Known Activations