© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39407
    Prev
    Next
    INDEX
    Explanations

    AP, Eng, pl, Trans, APE, aut, ves

    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
    çī¹åĭĴ
    -0.07
     maxLength
    -0.07
     maxlength
    -0.07
    è¾ĥéķ¿çļĦ
    -0.07
     Giles
    -0.07
    ยาว
    -0.07
    maxLength
    -0.07
    ook
    -0.07
    ro
    -0.07
    éĤ®å±Ģ
    -0.06
    POSITIVE LOGITS
     xì
    0.08
    峪
    0.08
    æľ¬ç¤¾
    0.08
    uild
    0.07
    çĭ¸
    0.07
    ordering
    0.07
    æĸ¹ä¾¿
    0.07
    ä¼ļè®®ä¸Ńå¿ĥ
    0.07
    endif
    0.07
    nty
    0.07
    Activations Density 0.011%

    No Known Activations