© 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. 89357
    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
    åįł
    -0.30
     tallest
    -0.29
    ç¾İåĽ½äºº
    -0.28
    åİ¥
    -0.28
    anos
    -0.27
     earm
    -0.27
    ìļ±
    -0.26
    alez
    -0.24
     Photographer
    -0.24
    èĩĨ
    -0.24
    POSITIVE LOGITS
    gree
    0.28
    åĽŀæĿ¥äºĨ
    0.24
     licences
    0.23
    æĶ¹æĪIJ
    0.23
    è£ħå¤ĩåĪ¶éĢł
    0.23
    è¿Ļç§į
    0.23
    thon
    0.23
    æĶ¹åĪ¶
    0.22
     mission
    0.22
    yl
    0.22
    Activations Density 3.760%

    No Known Activations

    This feature has no known activations.