© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7005
    Prev
    Next
    INDEX
    Explanations

    Non-English language snippets

    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
    ãĥ³ãĥĪ
    -0.28
    çķĻ
    -0.28
    è¿ĺæĺ¯
    -0.25
    array
    -0.25
    lys
    -0.25
    اÙħØ©
    -0.25
     menn
    -0.24
     Dayton
    -0.24
    IDA
    -0.24
     Fotos
    -0.24
    POSITIVE LOGITS
    è°ģçŁ¥
    0.30
    quist
    0.28
    社ä¼ļåıijå±ķ
    0.26
     togg
    0.26
    ìĸ´ìķ¼
    0.25
    ç§ijåĪĽ
    0.25
    elix
    0.25
    orbit
    0.25
    itte
    0.24
     conservation
    0.23
    Activations Density 0.938%

    No Known Activations