© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56844
    Prev
    Next
    INDEX
    Explanations

    integer, cost, or value

    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
    æĺŁæľŁåĽĽ
    -0.08
    ТС
    -0.08
    orts
    -0.07
    æłı
    -0.07
    ince
    -0.07
    Ñģно
    -0.07
    ceaux
    -0.07
    oux
    -0.07
    abra
    -0.07
    leurs
    -0.07
    POSITIVE LOGITS
    wali
    0.07
     Tell
    0.07
    ovich
    0.07
     Ere
    0.07
    人士
    0.06
    é«ĺå³°
    0.06
    å¸Ĥæ°ijæĶ¿å±Ģ
    0.06
    åIJijéĺ³
    0.06
    æķ°æį®åŃĺåĤ¨
    0.06
    umat
    0.06
    Activations Density 0.021%

    No Known Activations