© 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. 13766
    Prev
    Next
    INDEX
    Explanations

    single

    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
    etics
    -0.09
    omic
    -0.09
    ilent
    -0.08
    etic
    -0.08
    æ»ĭ
    -0.08
    rides
    -0.08
    ãĥ¼ãĥĦ
    -0.08
    acken
    -0.07
    oir
    -0.07
    ths
    -0.07
    POSITIVE LOGITS
    /single
    0.21
    (single
    0.18
     single
    0.15
    -single
    0.14
    Single
    0.13
    single
    0.13
    åįķ
    0.13
     Single
    0.13
    çļĦåįķ
    0.12
    æĪĸå¤ļ
    0.12
    Activations Density 0.167%

    No Known Activations