© 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. 23757
    Prev
    Next
    INDEX
    Explanations

    propositions and lemmas

    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
    è¿Ħ
    -0.08
    ursed
    -0.07
    ernen
    -0.07
    ắp
    -0.07
    minent
    -0.07
    ìļ©ìľ¼ë¡ľ
    -0.07
    жай
    -0.07
    -controls
    -0.07
    å¸ĮæľĽèĩªå·±
    -0.07
    ames
    -0.07
    POSITIVE LOGITS
     Lemma
    0.08
    æĿİ大
    0.07
    oux
    0.07
    Smooth
    0.07
    ç¿©ç¿©
    0.07
    iid
    0.06
    aley
    0.06
    Singleton
    0.06
    æıIJåĩºçļĦ
    0.06
     veter
    0.06
    Activations Density 0.007%

    No Known Activations