© 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. 32097
    Prev
    Next
    INDEX
    Explanations

    palindromic numbers, primes, squares

    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
    å¦Ĥæŀľè§īå¾Ĺ
    -0.07
    -mounted
    -0.07
    ilton
    -0.07
    ierre
    -0.07
    æı£
    -0.07
    umph
    -0.07
    oute
    -0.07
    ellerie
    -0.07
    åį³åı¯å®ĮæĪIJ
    -0.07
    ç¨
    -0.07
    POSITIVE LOGITS
    /non
    0.07
    ä¸İéĿŀ
    0.07
    åĴĮéĿŀ
    0.07
    åĪ¤å®ļ
    0.06
    边走
    0.06
     cheat
    0.06
    Orient
    0.06
    elli
    0.06
    åĴĮè°IJ
    0.06
    oglio
    0.06
    Activations Density 0.026%

    No Known Activations