© 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. 12536
    Prev
    Next
    INDEX
    Explanations

    related subject or material

    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
    ä¸İä¼Ĺ
    -0.07
    å«Į
    -0.07
    GMEM
    -0.06
    -0.06
    ä¸Ĭ
    -0.06
    åĽŀé¦ĸ
    -0.06
    sker
    -0.06
    è¡Ĩ
    -0.06
    izie
    -0.06
    ±
    -0.06
    POSITIVE LOGITS
    جا
    0.11
    é¢ĨåŁŁçļĦ
    0.10
    noch
    0.09
    CanBe
    0.08
    пло
    0.08
    iating
    0.08
    enste
    0.08
    ستا
    0.08
    anth
    0.07
    подоб
    0.07
    Activations Density 0.022%

    No Known Activations