© 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. 87428
    Prev
    Next
    INDEX
    Explanations

    yled

    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
     Hemisphere
    -0.07
    חודש
    -0.07
     ö
    -0.07
    empo
    -0.07
    眼睛
    -0.07
     бер
    -0.06
    쏠
    -0.06
    -router
    -0.06
    也好
    -0.06
     channels
    -0.06
    POSITIVE LOGITS
    目标
    0.07
    ylon
    0.07
    ὰ
    0.07
    arta
    0.06
    ないように
    0.06
     OnePlus
    0.06
    ساهم
    0.06
    rgctx
    0.06
     redevelopment
    0.06
    .Rendering
    0.06
    Activations Density 0.001%

    No Known Activations