© 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. 41614
    Prev
    Next
    INDEX
    Explanations

    phrases and quotes

    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
    umph
    -0.08
    mtree
    -0.07
    ra
    -0.07
    CIO
    -0.07
    enville
    -0.07
    itzt
    -0.07
    arren
    -0.07
    inkt
    -0.07
    çĹħæĥħåĪĨæŀIJ
    -0.07
    Anal
    -0.07
    POSITIVE LOGITS
     memor
    0.08
     remembered
    0.08
    åĩºå¤Ħ
    0.08
     remembering
    0.07
    è®°å¿Ĩ
    0.07
     classics
    0.07
    æĿ¥èĩª
    0.07
    çĸĻ
    0.07
    lei
    0.07
    åºĶçŃĶ
    0.07
    Activations Density 0.002%

    No Known Activations