© 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. 5788
    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
     ÑĢаÑģпÑĢоÑģÑĤ
    -0.25
    â¼Ĵ
    -0.25
    å°Ĭ严
    -0.24
    çļĦä¸ĢåĪĩ
    -0.24
     Wick
    -0.24
    éĶĢ
    -0.23
    uess
    -0.23
     Honour
    -0.23
    å¿ħçĦ¶ä¼ļ
    -0.23
    WORDS
    -0.23
    POSITIVE LOGITS
    åħ³ç³»
    0.26
     unc
    0.26
    anship
    0.25
    onia
    0.24
     bel
    0.24
    pet
    0.23
    ä¹ĭ家
    0.23
    ks
    0.23
    mine
    0.23
    åºľ
    0.23
    Activations Density 0.185%

    No Known Activations

    This feature has no known activations.