© 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. 23-TRANSCODER-HP
    7. 24739
    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
    _qual
    -0.28
    èĢħçļĦ
    -0.25
    Already
    -0.25
     lab
    -0.24
     Say
    -0.24
    feit
    -0.24
    ãģ¡ãģ¯
    -0.24
    tsy
    -0.24
     qual
    -0.23
    éĻ¢
    -0.23
    POSITIVE LOGITS
    Ñĥни
    0.28
    èĸĦ
    0.27
    åĭĺå¯Ł
    0.26
    ushman
    0.25
    éģŃéģĩ
    0.25
    mort
    0.24
    inch
    0.24
    aldi
    0.24
    vents
    0.24
    formula
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.