© 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. 33824
    Prev
    Next
    INDEX
    Explanations

    comparing things

    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
    ä¹ĭæīĢ以
    -0.08
    å¸ĮæľĽåľ¨
    -0.07
    çĶ±äºİåħ¶
    -0.07
    ftype
    -0.07
    zan
    -0.06
    åĨħ容çĶ±
    -0.06
    ÙĬرÙĩ
    -0.06
    otype
    -0.06
    hips
    -0.06
    æĹłèĻij
    -0.06
    POSITIVE LOGITS
     another
    0.08
    å®ŀéĻħæĥħåĨµ
    0.08
     other
    0.08
     пÑĢиз
    0.08
    another
    0.08
    å°±çŁ¥éģĵäºĨ
    0.07
    ä¾ĭåŃIJ
    0.07
     different
    0.07
     дÑĢÑĥгой
    0.07
    å·¥ä½ľå®ŀéĻħ
    0.07
    Activations Density 0.024%

    No Known Activations