© 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. 32690
    Prev
    Next
    INDEX
    Explanations

    listing multiple items

    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
    å¤ļ大çļĦ
    -0.08
    æľīä¸īç§į
    -0.07
    енеÑĢа
    -0.07
    ucks
    -0.07
    ä¸īéĿ¢
    -0.07
    è¢ħ
    -0.06
    æīĢ以ä»ĸ
    -0.06
    coder
    -0.06
    åħ¶äºĭ
    -0.06
    odaw
    -0.06
    POSITIVE LOGITS
    è¿ĺæľīå¾Īå¤ļ
    0.12
    è¿ĺæľī许å¤ļ
    0.11
    è¿ĺæľīåħ¶ä»ĸ
    0.10
    è¿ĺæľīä¸ĢäºĽ
    0.09
    è¿ĺæľī
    0.09
    çļĦåħ¶ä»ĸ
    0.09
    Weitere
    0.09
     اÙĦÙħزÙĬد
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    éĤĦæľī
    0.09
    Activations Density 0.144%

    No Known Activations