© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64308
    Prev
    Next
    INDEX
    Explanations

    Internet/Web related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isations
    -0.29
    uming
    -0.28
    etter
    -0.27
     далеко
    -0.26
    isation
    -0.25
     complic
    -0.24
    꺼
    -0.24
     Exterior
    -0.24
    ilig
    -0.24
    elves
    -0.24
    POSITIVE LOGITS
    uppy
    0.27
    gs
    0.26
    .randn
    0.26
    è¿Ľåİ»
    0.25
    ical
    0.25
    æĹı
    0.24
    ?family
    0.24
    åºĹéĿ¢
    0.24
    æĪijæĬĬ
    0.24
    _trace
    0.23
    Activations Density 10.517%

    No Known Activations