© 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. 88607
    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
    èĥĮ
    -0.27
    åĢ¾
    -0.27
    Esc
    -0.26
    æīĭèħķ
    -0.26
    pour
    -0.26
    atsu
    -0.25
    è´¢
    -0.24
    -cert
    -0.24
    çĿĢæīĭ
    -0.24
    watch
    -0.24
    POSITIVE LOGITS
    éķħ
    0.26
    çļĦåij½è¿IJ
    0.25
    .toLocale
    0.24
    ì²ľ
    0.24
    æĹ¥æ¶Īæģ¯
    0.24
    lete
    0.24
    GORITHM
    0.23
    uego
    0.23
     Yük
    0.23
    annt
    0.23
    Activations Density 42.170%

    No Known Activations

    This feature has no known activations.