© 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. 51192
    Prev
    Next
    INDEX
    Explanations

    comparisons with than or ago

    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
    ews
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    igram
    -0.07
    uffers
    -0.07
    otherwise
    -0.07
    åIJ¦åĪĻ
    -0.07
    mits
    -0.07
    .currentTime
    -0.07
    —for
    -0.07
    ç«Ļéķ¿
    -0.07
    POSITIVE LOGITS
    æķ´æķ´
    0.07
    çĪ½
    0.06
    è¿ľ
    0.06
    说æĺİ
    0.06
    icont
    0.06
    IAL
    0.06
     mengap
    0.06
    ouch
    0.06
     trend
    0.06
    éĻħ
    0.06
    Activations Density 0.036%

    No Known Activations