© 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. 917
    Prev
    Next
    INDEX
    Explanations

    intervals cover

    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
    LETE
    -0.08
    åľ¨åIJĦç§į
    -0.07
    zza
    -0.07
    nalis
    -0.07
    åħ¨éĿ¢åıijå±ķçļĦ
    -0.07
     prevailing
    -0.07
    该èĤ¡
    -0.07
    äºİè¡Į
    -0.07
     module
    -0.06
     Leg
    -0.06
    POSITIVE LOGITS
     disjoint
    0.09
    éĽĨåIJĪ
    0.08
    omar
    0.08
    天亮
    0.08
    _coverage
    0.08
     overlaps
    0.08
    Bounding
    0.07
     collection
    0.07
    åħĦå¼Łä»¬
    0.07
    _MAKE
    0.07
    Activations Density 0.008%

    No Known Activations