© 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. 40018
    Prev
    Next
    INDEX
    Explanations

    possible combinations

    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
    ä¸įæ±Ĥ
    -0.08
    nowrap
    -0.07
    æ»ĭ
    -0.07
    aum
    -0.07
    éģŀ
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    emos
    -0.07
    SOLE
    -0.07
    æĮģãģ¤
    -0.07
    umph
    -0.06
    POSITIVE LOGITS
     ways
    0.09
     candidate
    0.09
     possible
    0.09
    æĬĢæľ¯æĸ¹æ¡Ī
    0.08
     pair
    0.08
     combinations
    0.08
     configurations
    0.08
     configuration
    0.08
     paths
    0.08
    éĢĶå¾Ħ
    0.08
    Activations Density 0.136%

    No Known Activations