© 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. 43110
    Prev
    Next
    INDEX
    Explanations

    recoil, blowback, retracts, transverse, shake, pyomo

    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
    storm
    -0.08
    _EXIST
    -0.07
     regional
    -0.07
    æ»
    -0.07
    anoi
    -0.07
    alami
    -0.07
    ||||
    -0.06
    .au
    -0.06
     storm
    -0.06
     Midlands
    -0.06
    POSITIVE LOGITS
     recoil
    0.13
     reco
    0.09
    çīµè¿ŀ
    0.08
     Reco
    0.08
     جÙĨب
    0.08
    à¸Ľà¸±
    0.07
    ä¸ĩä¸Ī
    0.07
    indy
    0.07
    ivia
    0.07
     fines
    0.07
    Activations Density 0.002%

    No Known Activations