© 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. 12-TRANSCODER-HP
    7. 22468
    Prev
    Next
    INDEX
    Explanations

    ora

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nings
    -0.26
    ÑĩаÑĤ
    -0.25
    аÑĨион
    -0.25
    é«ĺåĩº
    -0.25
    ycl
    -0.25
     ruling
    -0.25
    缺åı£
    -0.24
    aus
    -0.24
    tures
    -0.24
    licative
    -0.24
    POSITIVE LOGITS
    ä¸ĭ车
    0.28
    _listener
    0.27
    ä¸ĭ乡
    0.27
    æ³¾
    0.26
    æĤ¨çļĦåŃ©åŃIJ
    0.26
     inputs
    0.25
    ä¸ĭçıŃ
    0.25
    骧
    0.24
     Inputs
    0.24
    è¾ĵç»Ļ
    0.24
    Activations Density 0.001%

    No Known Activations