© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161820
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ家
    -0.32
    èµĭ
    -0.30
    âĹĭ
    -0.29
    eman
    -0.28
     verk
    -0.26
    åģ¥åº·
    -0.25
    è¿Ļ款
    -0.25
    oce
    -0.25
    geb
    -0.24
    è¿Ļ家åħ¬åı¸
    -0.24
    POSITIVE LOGITS
    éļĻ
    0.28
     Rutgers
    0.27
     NU
    0.26
     CharSequence
    0.25
    æ±°
    0.25
    orney
    0.25
    $body
    0.24
     bình
    0.24
    SURE
    0.24
    _glob
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.