© 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. 18-TRANSCODER-HP
    7. 89711
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isons
    -0.28
    ationToken
    -0.24
    fect
    -0.24
    Scoped
    -0.24
     sexually
    -0.24
     Gros
    -0.24
    lint
    -0.23
    éĩijå¥ĸ
    -0.23
    ity
    -0.23
    ercial
    -0.23
    POSITIVE LOGITS
     transitions
    0.29
    亡
    0.28
    æĴ¤
    0.27
     Oakland
    0.27
    /de
    0.27
    ell
    0.27
    è´Ł
    0.27
     negative
    0.27
    åĨįåİ»
    0.26
    olg
    0.26
    Activations Density 47.461%

    No Known Activations