© 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. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43085
    Prev
    Next
    INDEX
    Explanations

    Asian names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.32
    è²Į
    -0.31
     ton
    -0.28
    od
    -0.26
     depression
    -0.25
     Od
    -0.24
    棣
    -0.24
     bumps
    -0.24
    odate
    -0.24
    icl
    -0.24
    POSITIVE LOGITS
     circ
    0.29
    thouse
    0.27
    -js
    0.26
    èįĨå·ŀ
    0.26
    rase
    0.24
    agy
    0.24
    trusted
    0.24
    èľľ
    0.24
    zan
    0.24
     pe
    0.24
    Activations Density 0.001%

    No Known Activations