© 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. 5385
    Prev
    Next
    INDEX
    Explanations

    technical reports/procedures

    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
     inventor
    -0.27
    ä¸ĢæĶ¯
    -0.26
    INDER
    -0.25
    anj
    -0.24
    çļĦåľ°
    -0.24
    меÑĤ
    -0.24
    @interface
    -0.24
    selectors
    -0.23
    æıIJä¾Ľä¼ĺè´¨
    -0.23
    /renderer
    -0.23
    POSITIVE LOGITS
    ovan
    0.28
    quot
    0.28
    onas
    0.27
    象å¾ģ
    0.27
    触
    0.26
    onomic
    0.26
    ucc
    0.26
    oola
    0.26
    asking
    0.26
    æ´µ
    0.25
    Activations Density 0.023%

    No Known Activations