© 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 EvalsExportsinterp-engineNEWAPI 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. 108340
    Prev
    Next
    INDEX
    Explanations

    code involving names

    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
    写了
    -0.07
     pics
    -0.07
    حصر
    -0.06
    רוץ
    -0.06
    出现了
    -0.06
     tongue
    -0.06
    -yard
    -0.06
     giọng
    -0.06
    hits
    -0.06
     IDS
    -0.06
    POSITIVE LOGITS
     החדש
    0.08
     トラ
    0.07
    クロ
    0.07
    Edward
    0.07
    源源
    0.07
    肇庆
    0.07
    .getFloat
    0.07
     maur
    0.07
     insane
    0.07
     supérieur
    0.07
    Activations Density 0.001%

    No Known Activations