© 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. 30370
    Prev
    Next
    INDEX
    Explanations

    micro

    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
    åŃ£
    -0.29
    è·¨
    -0.29
    èĽŁ
    -0.28
    DL
    -0.27
    ient
    -0.26
    ·¨
    -0.26
    ientos
    -0.26
    appoint
    -0.26
    owl
    -0.25
    iento
    -0.25
    POSITIVE LOGITS
     CONTRIBUTORS
    0.26
     anarch
    0.25
    .FALSE
    0.24
    èĥª
    0.24
    éĩĮéĿ¢æľī
    0.24
    .kill
    0.23
    atility
    0.23
    棻
    0.23
    æĹ¥æĬ¥ç¤¾
    0.23
     logical
    0.23
    Activations Density 2.954%

    No Known Activations