© 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. 5269
    Prev
    Next
    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash
    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
    æĮĩ导ä¸ĭ
    -0.25
    ellen
    -0.25
     reproduced
    -0.25
    对ä»ĺ
    -0.25
    sein
    -0.25
    Powered
    -0.24
    æĻ®éĢļ人
    -0.24
    -signed
    -0.24
    ä»
    -0.23
    icap
    -0.23
    POSITIVE LOGITS
    çIJĨ
    0.27
    _arguments
    0.26
     realloc
    0.25
     favoured
    0.25
    	pthread
    0.25
    大çļĦ
    0.24
    ениÑı
    0.24
    åīĶ
    0.24
    лÑĥ
    0.24
     external
    0.23
    Activations Density 0.007%

    No Known Activations