© 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. 25119
    Prev
    Next
    INDEX
    Explanations

    findings or results

    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
    onge
    -0.09
    ierung
    -0.08
    絡
    -0.08
    onger
    -0.08
    _defined
    -0.08
    èijĨ
    -0.07
    nement
    -0.07
    åĪĨä¹ĭä¸Ģ
    -0.07
    Ŀ
    -0.07
    illo
    -0.07
    POSITIVE LOGITS
    /results
    0.16
     results
    0.15
    results
    0.13
     Results
    0.12
     findings
    0.12
    Results
    0.11
    -results
    0.11
    ç»ĵæŀľ
    0.11
    .results
    0.11
    è¿ĻäºĽæķ°æį®
    0.10
    Activations Density 0.144%

    No Known Activations