© 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. 163780
    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
     decay
    -0.29
     tu
    -0.28
    asta
    -0.28
    tu
    -0.28
    人èĦī
    -0.26
    ç»Ħ
    -0.26
    çŃī级
    -0.26
    úa
    -0.25
    ä¿®
    -0.25
    repeat
    -0.25
    POSITIVE LOGITS
    å·²å®ĮæĪIJ
    0.29
    _MISS
    0.29
    ogs
    0.27
    (done
    0.27
     imported
    0.26
    à¤ĵ
    0.26
     accompl
    0.26
    ¬´
    0.25
     OTA
    0.25
    -engine
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.