© 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. 24294
    Prev
    Next
    INDEX
    Explanations

    mathematical context or notes

    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
    _blocking
    -0.08
    geries
    -0.08
    æ²ĥæĸ¯
    -0.08
    ÛĮب
    -0.08
    éĤ£æĿ¡
    -0.08
    ikov
    -0.08
    attes
    -0.08
    داد
    -0.07
    åijĺçļĦ
    -0.07
    rier
    -0.07
    POSITIVE LOGITS
     Sujet
    0.06
    è¶ħéĻIJ
    0.06
     consolidated
    0.06
    canvas
    0.06
    å¿łäºİ
    0.06
    åĪ¨
    0.06
    æĹ©æķĻ
    0.06
    çĴIJ
    0.06
    ôte
    0.06
     ly
    0.06
    Activations Density 0.004%

    No Known Activations