© 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. 163799
    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
    arez
    -0.29
    wealth
    -0.26
    é¦ı
    -0.25
    zar
    -0.25
    èĥĻ
    -0.25
    afx
    -0.24
    zek
    -0.23
    LEM
    -0.23
    åĽ½éĻħæľºåľº
    -0.23
     laboratory
    -0.23
    POSITIVE LOGITS
    äºĭæĥħ
    0.32
    äºĴ
    0.29
    äºĴåĬ©
    0.27
    åŃº
    0.25
     Ups
    0.25
    èľ·
    0.25
    éĶģ
    0.25
    åºķ
    0.25
    umi
    0.25
    æķ´
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.