© 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. 42575
    Prev
    Next
    INDEX
    Explanations

    inherit

    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
     ER
    -0.08
    春季
    -0.07
     Winter
    -0.07
    .u
    -0.07
     elk
    -0.07
     smtp
    -0.07
    aptors
    -0.07
    �
    -0.07
    触れ
    -0.06
    unter
    -0.06
    POSITIVE LOGITS
     territory
    0.07
     Bitcoins
    0.07
    _VARIABLE
    0.07
     based
    0.07
     댓글
    0.07
    cki
    0.07
    izada
    0.07
    novation
    0.06
    AccountId
    0.06
    问卷
    0.06
    Activations Density 0.010%

    No Known Activations