© 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. 163007
    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
    swer
    -0.30
    etz
    -0.29
     h
    -0.27
    StatusLabel
    -0.27
    ä½ĵéªĮ
    -0.25
    andom
    -0.25
    _placeholder
    -0.25
    eger
    -0.25
     Inn
    -0.24
    ods
    -0.24
    POSITIVE LOGITS
     stocks
    0.29
    ilan
    0.28
    è¿Ļåľº
    0.28
     ['#
    0.27
    wind
    0.26
    è¿Ļå¼ł
    0.26
    è¿Ļ项
    0.26
    çľ¼çļ®
    0.25
     Stocks
    0.25
    é£İäºij
    0.25
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.