© 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. 30935
    Prev
    Next
    INDEX
    Explanations

    vibration

    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
    eness
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    Äįin
    -0.09
    ward
    -0.09
    ValuePair
    -0.09
    ©
    -0.09
    为äºĨ解åĨ³
    -0.09
    æģ©æĸ¯
    -0.08
    edaran
    -0.08
    uvre
    -0.08
    POSITIVE LOGITS
    ä¸įæģ¯
    0.10
    çĿĢçļĦ
    0.09
    åĬ¨çļĦ
    0.09
    æłĹ
    0.08
    ä¸įå·²
    0.08
    ä¸įä¼ij
    0.08
    äºĨä¸Ģä¸ĭ
    0.07
    ante
    0.07
    uo
    0.07
    uating
    0.07
    Activations Density 0.021%

    No Known Activations