© 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. 29194
    Prev
    Next
    INDEX
    Explanations

    columnist

    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
     Guar
    -0.31
     guarantees
    -0.29
     hist
    -0.29
     historians
    -0.28
    rowsing
    -0.28
    guards
    -0.28
     pne
    -0.27
     exercise
    -0.27
    Hist
    -0.27
    ertino
    -0.26
    POSITIVE LOGITS
    .bundle
    0.28
    PEC
    0.27
     trib
    0.27
    æĭĪ
    0.27
    Wil
    0.26
     Pilot
    0.25
     cus
    0.25
     Trib
    0.25
     fit
    0.25
    èĽ®
    0.25
    Activations Density 2.814%

    No Known Activations