© 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. 19007
    Prev
    Next
    INDEX
    Explanations

    Core tip:**

    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
    и
    -0.08
    æīĢ以ä»ĸ们
    -0.08
    celona
    -0.08
    strup
    -0.07
    пиÑģÑĮ
    -0.07
    igm
    -0.07
    ilarity
    -0.07
    licer
    -0.07
    æīĢ以大家
    -0.07
    ä½Ĩæĺ¯ä»ĸ们
    -0.07
    POSITIVE LOGITS
    edList
    0.11
    avig
    0.07
    度çļĦ
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    াতà§ĩ
    0.07
    ém
    0.07
    aÅĤ
    0.07
    emo
    0.07
    >').
    0.06
    ħ
    0.06
    Activations Density 0.002%

    No Known Activations