© 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. 15327
    Prev
    Next
    INDEX
    Explanations

    proceed to

    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
    oros
    -0.09
    گذارÛĮ
    -0.08
    贴士
    -0.08
    ölcs
    -0.08
    ìĥī
    -0.08
    onne
    -0.08
    ÙİعÙĴ
    -0.08
    꽤
    -0.07
    addin
    -0.07
    orti
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    ä¸įä¸ĭåİ»
    0.08
    Ø©
    0.08
    ä¸įä¸ĭåİ»äºĨ
    0.08
     to
    0.08
    iab
    0.07
     toward
    0.07
    ledged
    0.07
    äºĨä¸ĢæŃ¥
    0.07
    以ä¸ĭæŃ¥éª¤
    0.07
    Activations Density 0.027%

    No Known Activations