© 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. 48441
    Prev
    Next
    INDEX
    Explanations

    academic/technical writing

    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
     başvuru
    -0.07
    以人为
    -0.07
    反而
    -0.07
     лишь
    -0.07
    サービス
    -0.07
    흉
    -0.07
     IA
    -0.06
    口コミ
    -0.06
    -ref
    -0.06
     저
    -0.06
    POSITIVE LOGITS
    meter
    0.07
    (er
    0.07
     ure
    0.07
    zeigen
    0.07
     Blue
    0.07
    ்�
    0.06
    签署
    0.06
    _il
    0.06
    ¬
    0.06
    _TRIANGLE
    0.06
    Activations Density 0.138%

    No Known Activations