© 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. 57374
    Prev
    Next
    INDEX
    Explanations

    possibility of

    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
     bestimm
    -0.07
    ahre
    -0.07
    erto
    -0.07
    umat
    -0.06
    .material
    -0.06
    νÏİ
    -0.06
    çļĭ
    -0.06
    **”
    -0.06
    ynchronize
    -0.06
    npj
    -0.06
    POSITIVE LOGITS
     اÛĮÙĨÚ©Ùĩ
    0.09
    è¿Ļæł·çļĦæĥħåĨµ
    0.08
    wier
    0.08
     ingle
    0.08
    åı¦å¤ĸä¸Ģç§į
    0.08
    æĬĬè¿Ļ个
    0.07
    å¦Ĥæŀľåıªæĺ¯
    0.07
    odore
    0.07
     possibility
    0.07
    baugh
    0.07
    Activations Density 0.028%

    No Known Activations