© 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. 162251
    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
    ç½Ħ
    -0.30
    MSN
    -0.28
     tolerated
    -0.26
    ="__
    -0.25
    eb
    -0.25
    vê
    -0.24
    ä½³
    -0.24
    äºĴéĢļ
    -0.24
    ells
    -0.23
    gatsby
    -0.23
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.29
    è¿Ļæĺ¯æĪij们
    0.28
    ani
    0.27
    æĺ¯æĪij
    0.27
    è¿Ļæĺ¯
    0.27
    è¿Ļæĺ¯æĪij
    0.26
    è¿Ļæĺ¯ä¸Ģ个
    0.25
    Focus
    0.25
    迹象
    0.24
    éĨ¢
    0.24
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.