© 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. 161887
    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
    heimer
    -0.28
    switch
    -0.28
    ston
    -0.28
     Caldwell
    -0.26
    ecast
    -0.26
    ç»ıèIJ¥æ¨¡å¼ı
    -0.25
    FM
    -0.25
    çĶŁæ´»æĸ¹å¼ı
    -0.24
    è°Īè¯Ŀ
    -0.24
    çŀ°
    -0.24
    POSITIVE LOGITS
     code
    0.26
    天涯
    0.26
     affiliate
    0.26
    âĶĶ
    0.26
     her
    0.26
    å¦Ĥæŀľæ²¡æľī
    0.25
     default
    0.25
     Held
    0.25
    大éĻ¸
    0.25
     bound
    0.24
    Activations Density 0.052%

    No Known Activations

    This feature has no known activations.