© 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. 63218
    Prev
    Next
    INDEX
    Explanations

    order or rule

    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
    æł¹æį®å®ŀéĻħæĥħåĨµ
    -0.08
    åľ¨åģļ好
    -0.08
    ife
    -0.08
    éħ¸çĶľ
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.07
    æľīåħ³æ³ķå¾ĭæ³ķè§Ħ
    -0.07
    æľīåħ³äººåijĺ
    -0.07
    ÅĻÃŃzenÃŃ
    -0.07
    举åįĩ
    -0.07
    anal
    -0.07
    POSITIVE LOGITS
     precisely
    0.07
    .medium
    0.07
     trans
    0.06
    éĢıåĩº
    0.06
    å®ĥæīĢ
    0.06
     philosophers
    0.06
     exile
    0.06
     juxtap
    0.06
    ä¸įèµ·
    0.06
    毫ä¸į
    0.06
    Activations Density 0.008%

    No Known Activations