© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 40813
    Prev
    Next
    INDEX
    Explanations

    locations and organizations

    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
    Negative Logits
    han
    -0.28
    RX
    -0.28
    幡
    -0.26
    kal
    -0.25
     Bom
    -0.25
    Lex
    -0.25
    hal
    -0.25
    Ep
    -0.24
    hawks
    -0.24
    idor
    -0.24
    POSITIVE LOGITS
    erset
    0.28
    å¯Ĩ度
    0.25
     bedtime
    0.25
    UDA
    0.25
     PM
    0.24
     densities
    0.24
     density
    0.24
    -density
    0.23
    /pm
    0.23
    matter
    0.23
    Activations Density 0.001%

    No Known Activations