© 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. 162631
    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
    åįĴ
    -0.30
    ï¼Į“
    -0.28
    inium
    -0.28
    mlink
    -0.27
    çŀ¿
    -0.27
    chet
    -0.26
    utations
    -0.25
    çķĻåŃĺ
    -0.25
     Uph
    -0.25
    aged
    -0.25
    POSITIVE LOGITS
    åľ¨çº¿
    0.30
     press
    0.27
     partially
    0.25
    _PRESS
    0.25
     partly
    0.25
     fraction
    0.25
    itives
    0.24
    ãģľ
    0.24
     races
    0.24
    erializer
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.