© 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. 9-TRANSCODER-HP
    7. 29344
    Prev
    Next
    INDEX
    Explanations

    band

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zar
    -0.35
    bands
    -0.32
    band
    -0.30
    Band
    -0.30
     bands
    -0.28
    itespace
    -0.28
     Band
    -0.28
    inos
    -0.27
    .band
    -0.27
     band
    -0.26
    POSITIVE LOGITS
    -elect
    0.25
     strikes
    0.24
     hysteria
    0.24
     Strikes
    0.24
     Emb
    0.24
    羣å®ŀ
    0.23
    hoa
    0.23
    éĽĩä½£
    0.23
    aan
    0.23
     allocations
    0.23
    Activations Density 2.453%

    No Known Activations