© 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. 4287
    Prev
    Next
    INDEX
    Explanations

    populate table or data structure

    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
    erman
    -0.07
    车æµģ
    -0.07
    为äºĨæĽ´å¥½çļĦ
    -0.07
    forc
    -0.07
     Lesser
    -0.06
    ottle
    -0.06
    å°ĨæīĢæľī
    -0.06
     snatch
    -0.06
    åľ¨åĨľæĿij
    -0.06
    atin
    -0.06
    POSITIVE LOGITS
    åĪ°æĿ¥
    0.08
    yste
    0.08
    ä¸Ģ缴å¤Ħäºİ
    0.08
    个人ç®ĢåİĨ
    0.08
     Dest
    0.08
    hana
    0.07
     downstream
    0.07
    ujo
    0.07
    iev
    0.07
    ISMO
    0.07
    Activations Density 0.265%

    No Known Activations