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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163477
    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
    addy
    -0.29
    zew
    -0.26
    zem
    -0.24
    大å¸Ī
    -0.24
    module
    -0.24
     Ãĩ
    -0.23
    classname
    -0.23
    меÑģ
    -0.23
    Speech
    -0.23
    大å¦Ī
    -0.23
    POSITIVE LOGITS
    _LP
    0.26
    usta
    0.25
    oined
    0.24
    _ABC
    0.24
    _frames
    0.24
    aras
    0.23
    åIJĦæł·
    0.23
    çĶŁäº§çº¿
    0.23
    _LL
    0.23
    åIJĦè¡Į
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.