© 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. 85418
    Prev
    Next
    INDEX
    Explanations

    over

    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
    شع
    -0.07
    ','','
    -0.07
    /my
    -0.07
    iju
    -0.07
    ANS
    -0.07
     Yus
    -0.07
     atmos
    -0.07
     champs
    -0.06
     Ambient
    -0.06
    icro
    -0.06
    POSITIVE LOGITS
    辟
    0.08
     router
    0.07
    (JSON
    0.07
     Eisen
    0.07
    =float
    0.07
    .Sort
    0.07
    bef
    0.06
    Router
    0.06
    "Oh
    0.06
     IntelliJ
    0.06
    Activations Density 0.007%

    No Known Activations