© 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. 3754
    Prev
    Next
    INDEX
    Explanations

    regress against itself

    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
    eis
    -0.08
    Uns
    -0.08
     Uns
    -0.08
    arkin
    -0.08
    ij¸
    -0.08
    abat
    -0.07
    uket
    -0.07
     sát
    -0.07
    æıIJé«ĺå·¥ä½ľæķĪçİĩ
    -0.07
    央
    -0.07
    POSITIVE LOGITS
    èĩªå·±
    0.11
     ÑģебÑı
    0.11
    æľ¬äºº
    0.10
    çļĦèĩªå·±
    0.10
     Ñģебе
    0.10
    èĩªå·±éĥ½
    0.09
    对èĩªå·±çļĦ
    0.09
    _SELF
    0.09
     oneself
    0.09
    对èĩªå·±
    0.08
    Activations Density 0.011%

    No Known Activations