© 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. 9408
    Prev
    Next
    INDEX
    Explanations

    comparing important qualitative descriptions

    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
    羨
    -0.09
    yiz
    -0.09
    ëĭī
    -0.08
    ä½ĻåĬĽ
    -0.08
    ssia
    -0.07
    guer
    -0.07
    ×IJ×ķת
    -0.07
    ìĦľëĬĶ
    -0.07
    öt
    -0.07
    sWith
    -0.07
    POSITIVE LOGITS
     compared
    0.07
    rh
    0.07
     demais
    0.06
    æ°¸æģĴ
    0.06
    èĩ³æŀģ
    0.06
     Compared
    0.06
    ç»Ŀ对çļĦ
    0.06
    缸æ¯Ķ
    0.06
    æŀģäºĨ
    0.06
    æĬµ
    0.06
    Activations Density 0.164%

    No Known Activations