© 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. 30489
    Prev
    Next
    INDEX
    Explanations

    Technical document text

    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
    rang
    -0.27
    ä¸ŃåѦ
    -0.27
    继ç»Ńä¿ĿæĮģ
    -0.24
    rant
    -0.24
    enko
    -0.24
    orget
    -0.24
    AuthGuard
    -0.24
    èºı
    -0.23
    Publish
    -0.23
     literature
    -0.23
    POSITIVE LOGITS
     iota
    0.28
    aldi
    0.28
    igr
    0.26
    umer
    0.25
    INESS
    0.25
    ums
    0.24
    quential
    0.24
    ined
    0.24
    nero
    0.24
    cision
    0.24
    Activations Density 0.297%

    No Known Activations