© 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. 19-TRANSCODER-HP
    7. 5317
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æįĨç»ij
    -0.28
    _Tick
    -0.26
    æįĨ
    -0.25
    package
    -0.25
    -package
    -0.24
    azzi
    -0.24
     spac
    -0.24
    nt
    -0.24
    practice
    -0.23
    é¢IJ
    -0.23
    POSITIVE LOGITS
    ufig
    0.29
    éħĹ
    0.26
    ByExample
    0.26
    assis
    0.25
    åĪ«è¯´
    0.25
    åĿĩè¡¡
    0.24
    设å¤ĩ
    0.24
    ä¸Ģ头
    0.24
    peon
    0.23
    å²Ĺ
    0.23
    Activations Density 0.090%

    No Known Activations

    This feature has no known activations.