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

    Neuronpedia

    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. 40445
    Prev
    Next
    INDEX
    Explanations

    Punctuations/Symbols

    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
     reaching
    -0.08
     Prescott
    -0.07
    \:
    -0.07
    xdd
    -0.07
     görüyor
    -0.07
    どう
    -0.07
    اصة
    -0.07
     "
    -0.07
    FW
    -0.07
     Principal
    -0.07
    POSITIVE LOGITS
     Industry
    0.08
     метал
    0.07
     Marx
    0.07
     spirit
    0.07
    mere
    0.07
    แบร
    0.07
     fighter
    0.07
     Univers
    0.07
     Việt
    0.07
    냅
    0.07
    Activations Density 0.175%

    No Known Activations