© 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. 162508
    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
    post
    -0.28
    EventHandler
    -0.26
    definition
    -0.26
    put
    -0.26
    etus
    -0.26
    åĨ²
    -0.25
    ä¹ĭäºī
    -0.24
     slugg
    -0.24
     evapor
    -0.24
     appreciated
    -0.24
    POSITIVE LOGITS
    æ¡Į
    0.28
    æ¡ĮéĿ¢
    0.25
    ique
    0.25
    åı£
    0.24
    {}]
    0.24
    vore
    0.24
    ibi
    0.24
    ichte
    0.24
    åı°
    0.24
    =?,
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.