© 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. 88982
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     radi
    -0.28
     exploiting
    -0.28
    _drag
    -0.27
     exploit
    -0.27
    atica
    -0.27
     precondition
    -0.25
     CFR
    -0.24
    radi
    -0.24
    /+
    -0.24
    cla
    -0.24
    POSITIVE LOGITS
    纵
    0.27
    PRINTF
    0.25
    ç¼Ł
    0.25
    Ñĥл
    0.25
    ittal
    0.25
    ä¸įåģľ
    0.25
    etat
    0.25
    æİ¥åĪ°
    0.24
    åı¯ä»¥çĽ´æİ¥
    0.24
    aar
    0.24
    Activations Density 12.027%

    No Known Activations

    This feature has no known activations.