© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25057
    Prev
    Next
    INDEX
    Explanations

    register access

    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
    è¯Ńç§į
    -0.07
    gaz
    -0.07
    ç·
    -0.07
    IFI
    -0.07
    vfs
    -0.06
    æijĨäºĨ
    -0.06
    ÐĸÐĶ
    -0.06
     filet
    -0.06
     meeting
    -0.06
     manh
    -0.06
    POSITIVE LOGITS
    peater
    0.08
     Accessed
    0.08
    å¸Ī表
    0.08
    就读
    0.08
    volatile
    0.07
    _BANK
    0.07
    å¤įä½į
    0.07
     BANK
    0.07
    accessible
    0.07
    hart
    0.07
    Activations Density 0.052%

    No Known Activations