© 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. 163155
    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
    \Id
    -0.29
    ä¸īæľŁ
    -0.26
    IVATE
    -0.26
    idf
    -0.26
    带ä¸Ĭ
    -0.26
    -family
    -0.25
    istar
    -0.25
    aba
    -0.25
    inement
    -0.25
    ç½²
    -0.25
    POSITIVE LOGITS
    lowest
    0.27
    __:
    0.25
     yourselves
    0.25
    athan
    0.25
    .tight
    0.24
    ijľ
    0.24
    ürn
    0.24
    ÅĤow
    0.24
    elig
    0.23
    åIJĿ
    0.23
    Activations Density 0.054%

    No Known Activations

    This feature has no known activations.