© 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. 19-RESID-POST-AA
    11. 5800
    Prev
    Next
    INDEX
    Explanations

    support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ับ
    -0.08
    PID
    -0.07
     molt
    -0.07
     denen
    -0.07
     comb
    -0.07
     ming
    -0.07
     ber
    -0.06
    pole
    -0.06
     MaterialApp
    -0.06
    Α
    -0.06
    POSITIVE LOGITS
     FK
    0.07
     Removed
    0.07
    _reviews
    0.07
     bullet
    0.07
     )↵↵↵↵↵↵↵↵
    0.07
     북한
    0.07
     гаранти
    0.07
    '[
    0.07
    尤其是在
    0.07
    _increase
    0.07
    Activations Density 0.000%

    No Known Activations