© 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. 19-TRANSCODER-HP
    7. 8433
    Prev
    Next
    INDEX
    Explanations

    Code comments

    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
    ä¸į论æĺ¯
    -0.26
    ги
    -0.26
    intage
    -0.26
    å¿Į
    -0.25
    iske
    -0.24
    æĺ¯ä»ĸ
    -0.24
     wsp
    -0.24
    çļĦåIJĦç§į
    -0.23
    versions
    -0.23
    lö
    -0.23
    POSITIVE LOGITS
    ç«ŀäºī对æīĭ
    0.26
    erner
    0.25
    è¿ĩçļĦ
    0.24
    åĨ²
    0.24
    _xt
    0.24
    defined
    0.24
    XP
    0.24
    足
    0.24
    ocz
    0.24
    ERM
    0.24
    Activations Density 0.027%

    No Known Activations