© 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. 162431
    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
    à¹ĥà¸Ī
    -0.33
    à¹īà¸Ńà¸Ļ
    -0.28
     cyl
    -0.28
    eh
    -0.28
    nde
    -0.27
    cing
    -0.27
    ek
    -0.26
    éĴ®
    -0.25
    å¾Īå¿«
    -0.24
    çķĻç»Ļ
    -0.24
    POSITIVE LOGITS
     precision
    0.29
     Precision
    0.27
     subst
    0.26
     nationality
    0.26
     Surge
    0.25
     sites
    0.25
    åĬŀäºĭå¤Ħ
    0.25
     websites
    0.25
    /sites
    0.25
    _sites
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.