© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 34427
    Prev
    Next
    INDEX
    Explanations

    liquid

    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
    ANDLE
    -0.08
    Address
    -0.07
    (Grid
    -0.07
    期盼
    -0.07
    :"<<
    -0.06
    ADDR
    -0.06
    ⎓
    -0.06
    }",
    -0.06
    גוש
    -0.06
     area
    -0.06
    POSITIVE LOGITS
    站着
    0.07
     октя
    0.07
    孙悟
    0.07
    优秀
    0.07
    原始
    0.07
     đã
    0.06
    Enums
    0.06
    oxide
    0.06
    影片
    0.06
     worksheets
    0.06
    Activations Density 0.012%

    No Known Activations