© 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. 26561
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    ilda
    -0.07
    å·§
    -0.07
    ameda
    -0.06
     yyn
    -0.06
    æĩĤäºĨ
    -0.06
    jeÄį
    -0.06
    å¦Ĭ
    -0.06
    èĽĻ
    -0.06
    erg
    -0.06
    å·©
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭãģ®
    0.07
    wehr
    0.07
    ä¸ŃåĽ½åĵģçīĮ
    0.07
    åĭĴæĸ¯
    0.07
     patente
    0.07
    fera
    0.07
    ARO
    0.07
    ãĥķãĥĪ
    0.07
    hower
    0.07
     hö
    0.06
    Activations Density 0.018%

    No Known Activations