© 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. 88839
    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
     allo
    -0.32
    ilden
    -0.27
    aceous
    -0.25
    çļĦåij½è¿IJ
    -0.25
    çļĦæķ°éĩı
    -0.25
    èĪĶ
    -0.25
    Golden
    -0.24
    è¡¥åħħ
    -0.24
    ppy
    -0.24
    æĪIJ交
    -0.24
    POSITIVE LOGITS
     NOI
    0.26
    midi
    0.25
    åĪĨæľŁ
    0.25
     Loc
    0.24
    欲
    0.24
    NJ
    0.24
    ialis
    0.24
    HD
    0.24
    EFR
    0.23
    imals
    0.23
    Activations Density 1.173%

    No Known Activations

    This feature has no known activations.