© 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. 33-TRANSCODER-HP
    7. 52858
    Prev
    Next
    INDEX
    Explanations

    coding/foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imp
    -0.30
    /*----------------------------------------------------------------
    -0.25
     Vinci
    -0.25
     minim
    -0.25
    åIJ¦
    -0.25
    æį¢
    -0.25
    åĿļ强
    -0.25
    纤
    -0.24
    atten
    -0.24
    wheel
    -0.24
    POSITIVE LOGITS
    æĹ©æĻ¨
    0.30
    po
    0.27
    oda
    0.26
     sobie
    0.26
    EA
    0.26
    (dp
    0.25
    eton
    0.24
     dq
    0.24
    dq
    0.24
    по
    0.23
    Activations Density 0.010%

    No Known Activations