© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30347
    Prev
    Next
    INDEX
    Explanations

    coordinates or variables x,y,z

    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
    nitz
    -0.09
    åIJİèĢħ
    -0.08
     berdua
    -0.08
    ÏĢει
    -0.08
    åĪ¤å¤ĦæľīæľŁå¾ĴåĪij
    -0.08
    iten
    -0.08
    ä¸¤å¼ł
    -0.08
     ÙħÙĨÙĩÙħا
    -0.08
    tral
    -0.08
    ordu
    -0.08
    POSITIVE LOGITS
     etc
    0.07
    ãģĦãģļãĤĮ
    0.07
    ãģ¨ãģĦãģ£ãģŁ
    0.06
    etc
    0.06
     pairwise
    0.06
     respectiv
    0.06
     tiro
    0.06
    åIJĦåħ·
    0.06
    以åıĬä¸ĢäºĽ
    0.06
    antul
    0.06
    Activations Density 0.009%

    No Known Activations