© 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. 5897
    Prev
    Next
    INDEX
    Explanations

    FDA

    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
     fil
    -0.30
    afc
    -0.29
    acons
    -0.28
    æĺ¯ä»¥
    -0.28
    erate
    -0.27
    æľīä¸Ģ
    -0.26
    soc
    -0.25
    pert
    -0.24
     pert
    -0.24
    ائÙĬØ©
    -0.24
    POSITIVE LOGITS
    éļ¾æĢª
    0.29
    0.28
    SITE
    0.26
    riv
    0.25
    vvm
    0.24
    endez
    0.24
    ogie
    0.24
    .Imp
    0.24
    秫
    0.23
    åģļ好
    0.23
    Activations Density 0.020%

    No Known Activations