© 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. 88659
    Prev
    Next
    INDEX
    Explanations

    Articles/prepositions

    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
    Authority
    -0.29
    icker
    -0.25
    aeda
    -0.25
    iji
    -0.25
     Authority
    -0.23
    æľĢå¿«
    -0.23
    ije
    -0.23
     بتارÙĬØ®
    -0.23
    TableRow
    -0.23
    æĮij
    -0.23
    POSITIVE LOGITS
    åĤ¥
    0.25
    订éĺħ
    0.25
    çĮ¬
    0.24
     mắc
    0.24
     grooming
    0.24
    æĬ¥åijĬ
    0.24
    **↵
    0.23
    era
    0.23
    `↵
    0.23
    äººæł¼
    0.23
    Activations Density 34.765%

    No Known Activations