© 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. 44974
    Prev
    Next
    INDEX
    Explanations

    data analysis and methods

    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
    iggio
    -0.09
    amsung
    -0.07
    ä¸įç»Ŀ
    -0.07
    ebro
    -0.07
     inject
    -0.06
     slashed
    -0.06
    è¡ĮåĬ¨ä¸Ń
    -0.06
    åĮĹéĿ¢
    -0.06
    ked
    -0.06
    sti
    -0.06
    POSITIVE LOGITS
     analysis
    0.13
    å¤ĦçIJĨåIJİ
    0.12
    æķ°æį®åĪĨæŀIJ
    0.11
     processing
    0.11
     analyses
    0.11
    -analysis
    0.11
     Analysis
    0.11
    analysis
    0.11
    åĪĨæŀIJ
    0.11
    _analysis
    0.11
    Activations Density 0.380%

    No Known Activations