© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28757
    Prev
    Next
    INDEX
    Explanations

    Matthew, Lin, Chamber, Wu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntag
    -0.08
    afc
    -0.07
    _ALLOC
    -0.07
    ÑģнÑĥÑİ
    -0.07
    unate
    -0.07
    Ñĩан
    -0.07
    _scheme
    -0.07
    iai
    -0.07
    æ¡Ī
    -0.07
     tát
    -0.07
    POSITIVE LOGITS
    大家æĹı
    0.06
    avra
    0.06
    меÑĤÑĮ
    0.06
     rato
    0.06
     distra
    0.06
    íĥĪ
    0.06
    åĬłæĭ¿å¤§
    0.06
    reate
    0.05
    åħ¬æīĢ
    0.05
    wr
    0.05
    Activations Density 0.237%

    No Known Activations