© 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. 57673
    Prev
    Next
    INDEX
    Explanations

    parentheses and dollar signs

    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
    æŁ¥çľĭçŃĶæ¡Ī
    -0.07
    amal
    -0.07
     ?.
    -0.07
    áĢ°
    -0.06
    ató
    -0.06
    okia
    -0.06
    amaha
    -0.06
    گرد
    -0.06
    å¿ħ究
    -0.06
    èµŀè¿ĩ
    -0.06
    POSITIVE LOGITS
    æĢĢæı£
    0.07
    ssi
    0.07
    CTS
    0.06
    -et
    0.06
    .Dataset
    0.06
    ħ
    0.06
    å¼¥éĻĢ
    0.06
    Įĵ
    0.06
    Helpers
    0.06
    esan
    0.06
    Activations Density 0.012%

    No Known Activations