© 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. 37865
    Prev
    Next
    INDEX
    Explanations

    derivation and deriving

    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
    æľ¬ç½ij
    -0.08
    è¯Ħä»·ä½ĵç³»
    -0.07
    ä½ıäºĨ
    -0.07
    æ§
    -0.07
    anzeige
    -0.07
    ECH
    -0.07
    ovah
    -0.07
    çļĦè¯Ħä»·
    -0.07
    ldata
    -0.07
    midd
    -0.07
    POSITIVE LOGITS
     derivation
    0.16
    æݨ导
    0.14
     deriving
    0.13
     deriv
    0.11
     derive
    0.11
     Der
    0.10
    Der
    0.10
     derives
    0.10
    论è¯ģ
    0.09
    derive
    0.09
    Activations Density 0.049%

    No Known Activations