© 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. 19-TRANSCODER-HP
    7. 8413
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ATV
    -0.29
     SMART
    -0.28
     ect
    -0.27
    ective
    -0.26
    oval
    -0.26
     Highlander
    -0.25
     Yue
    -0.25
    SMART
    -0.25
     WHETHER
    -0.25
    :absolute
    -0.24
    POSITIVE LOGITS
    å¥Ī
    0.29
    esh
    0.27
    è¿Ļ个人
    0.26
     .
    0.26
     endure
    0.26
     span
    0.26
    路线
    0.26
    ç»Īäºİ
    0.25
     Grand
    0.25
     around
    0.25
    Activations Density 0.011%

    No Known Activations