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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 42553
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    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
    _rel
    -0.07
    -relative
    -0.07
    Ū
    -0.07
     gentle
    -0.07
     lif
    -0.07
    _link
    -0.07
    Ｉ
    -0.07
    骐
    -0.07
    ifes
    -0.06
    舔
    -0.06
    POSITIVE LOGITS
     concat
    0.07
     interpolation
    0.07
    监护
    0.06
     Platt
    0.06
     Battery
    0.06
     scrambling
    0.06
    :checked
    0.06
     rewrite
    0.06
    监察
    0.06
    .device
    0.06
    Activations Density 0.003%

    No Known Activations