© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150304
    Prev
    Next
    INDEX
    Explanations

    solution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ľè¥¿
    -0.27
    eways
    -0.25
    è¶Ĭæĺ¯
    -0.25
    æĿ±è¥¿
    -0.25
    ánÃŃ
    -0.24
    stddef
    -0.24
    è¿Ļ个游æĪı
    -0.24
    ä»»ä½ķæŶåĢĻ
    -0.23
     qb
    -0.23
     thing
    -0.23
    POSITIVE LOGITS
    ouce
    0.31
    wis
    0.28
    ä¿Ŀ
    0.28
    bo
    0.27
     guar
    0.27
    ä¸įç¦ģ
    0.26
    mand
    0.26
     rate
    0.25
     applied
    0.25
    ism
    0.25
    Activations Density 2.000%

    No Known Activations