© 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. 38903
    Prev
    Next
    INDEX
    Explanations

    Registered Golf and Reviews

    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
    aglio
    -0.07
    epam
    -0.07
    åħļçļĦäºĮåįģ大
    -0.07
    satz
    -0.06
    /cop
    -0.06
    æģĥ
    -0.06
    βο
    -0.06
    åĩºå¸ŃäºĨ
    -0.06
    éģįéĩİ
    -0.06
    ↵     ↵
    -0.06
    POSITIVE LOGITS
    å¹´åįİ
    0.08
    å§ĭèĩ³
    0.08
    ÑģмоÑĤÑĢиÑĤе
    0.08
    ároz
    0.07
    odate
    0.07
    inhas
    0.07
    Úµ
    0.07
    лиÑĢÑĥ
    0.06
     mãi
    0.06
    æľªæľī
    0.06
    Activations Density 0.030%

    No Known Activations