© 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. 44168
    Prev
    Next
    INDEX
    Explanations

    sh/osh

    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
    åģľä¸ĭ
    -0.29
    æĶ¸
    -0.28
     apt
    -0.27
    ir
    -0.26
    @stop
    -0.25
    ç¼Ļ
    -0.24
    Ñģол
    -0.24
    pton
    -0.24
    srv
    -0.24
    PRICE
    -0.23
    POSITIVE LOGITS
    abet
    0.32
    axy
    0.27
    agra
    0.27
     continental
    0.26
    DataContext
    0.25
    nic
    0.24
    oga
    0.24
    agr
    0.24
    Registr
    0.24
    ç»ĦåĽ¢
    0.24
    Activations Density 0.001%

    No Known Activations