© 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. 41887
    Prev
    Next
    INDEX
    Explanations

    this purpose or prognosis

    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
    assist
    -0.07
    رة
    -0.07
    á»±c
    -0.07
    æľīçļĦæĺ¯
    -0.07
    validators
    -0.07
    resse
    -0.07
    inton
    -0.07
    ì§ľ
    -0.07
    örden
    -0.07
    ëij¥
    -0.07
    POSITIVE LOGITS
     wÅĤaÅĽnie
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
     otherwise
    0.07
    è¿ĻèĪ¬
    0.06
     Otherwise
    0.06
    ä½łè¿Ļä¹Ī
    0.06
    cean
    0.06
    eck
    0.06
    æĬĬäºĭæĥħ
    0.06
    st
    0.06
    Activations Density 0.341%

    No Known Activations