© 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. 11-RESID-POST-AA
    11. 85468
    Prev
    Next
    INDEX
    Explanations

    зап

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    慈
    -0.08
    暫
    -0.08
    줍
    -0.08
    -non
    -0.07
     aj
    -0.07
    atta
    -0.07
    ignment
    -0.07
    나
    -0.07
    �
    -0.07
     side
    -0.07
    POSITIVE LOGITS
    entries
    0.08
     Jury
    0.07
    -scalable
    0.07
     Markets
    0.07
    .unpack
    0.07
     missiles
    0.07
     printers
    0.07
     reproduction
    0.07
     Anatomy
    0.07
     Chick
    0.07
    Activations Density 0.010%

    No Known Activations