© 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. 23997
    Prev
    Next
    INDEX
    Explanations

    offer links, pulse tracing, contact angle, glass industry

    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
    å¦Ĥæ½®
    -0.08
    åħļ群
    -0.08
    cidental
    -0.07
    stur
    -0.07
    è·Łä¸Ĭ
    -0.07
     tarn
    -0.07
    ypsy
    -0.07
     Tingkat
    -0.07
     tingkat
    -0.07
    ä¸Ńå±Ĥ
    -0.07
    POSITIVE LOGITS
     intercept
    0.09
    áz
    0.07
     mets
    0.07
    çĭ¬
    0.07
     alc
    0.07
     rabat
    0.07
     Oc
    0.07
     Bota
    0.07
    çĶ»æ³ķ
    0.07
     intersects
    0.07
    Activations Density 0.001%

    No Known Activations