© 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. 7293
    Prev
    Next
    INDEX
    Explanations

    differences between

    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
    èĵ¬
    -0.06
    äºĽ
    -0.06
     A
    -0.06
    Âł
    -0.06
    çļĦé«ĺéĢŁ
    -0.06
    ä¸İå®ŀéĻħ
    -0.06
     including
    -0.06
     Mim
    -0.06
    çĸ¾
    -0.06
    åı«ä»Ģä¹Ī
    -0.05
    POSITIVE LOGITS
     nhau
    0.09
    acular
    0.09
    åIJĦèĩªçļĦ
    0.09
    onha
    0.09
     alike
    0.09
    åIJĦèĩª
    0.09
    ERRU
    0.08
     respectiv
    0.08
    argout
    0.08
    è¿Ļ两ç§į
    0.08
    Activations Density 0.120%

    No Known Activations