© 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. 25-TRANSCODER-HP
    7. 109114
    Prev
    Next
    INDEX
    Explanations

    Non-English words/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exas
    -0.28
    layout
    -0.27
    æĺ¯æĪijåĽ½
    -0.27
    fn
    -0.25
    å¼ºåĽ½
    -0.25
    acades
    -0.24
    ¼
    -0.24
    ãģĵãĤĮãģĮ
    -0.24
     fn
    -0.24
     sched
    -0.24
    POSITIVE LOGITS
    ä½ľèĢħæīĢæľī
    0.29
    PyObject
    0.26
    issional
    0.25
    çݺ
    0.25
    æĢ»çļĦæĿ¥è¯´
    0.25
    @endif
    0.25
     tamp
    0.25
    pyx
    0.25
     PSI
    0.25
     cin
    0.25
    Activations Density 0.899%

    No Known Activations