© 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. 89911
    Prev
    Next
    INDEX
    Explanations

    Code and symbols

    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
    æݨ
    -0.25
    Ĭ¶æĢģ
    -0.25
    ged
    -0.25
    fed
    -0.24
    setVisibility
    -0.24
    heck
    -0.24
    ones
    -0.24
    èĭ£
    -0.23
     tav
    -0.23
     implicit
    -0.23
    POSITIVE LOGITS
    uai
    0.29
    ubber
    0.26
    èĽĽ
    0.25
    ambre
    0.24
    亲
    0.23
    uais
    0.23
    使çĶ¨æĿĥ
    0.23
    ereum
    0.23
    ãĥĸãĥ©
    0.23
    ipp
    0.22
    Activations Density 56.804%

    No Known Activations