© 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. 2265
    Prev
    Next
    INDEX
    Explanations

    school or grade level contexts

    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
    itol
    -0.08
    recken
    -0.07
    åħ±åº¦
    -0.07
    asco
    -0.07
    iones
    -0.07
     неÑı
    -0.07
     fools
    -0.07
    itif
    -0.07
    ìļĶ
    -0.07
    otos
    -0.07
    POSITIVE LOGITS
    ajs
    0.08
     /^\
    0.07
    à¸IJ
    0.07
     pun
    0.07
    rever
    0.07
    er
    0.07
    iller
    0.06
    大éĢļ
    0.06
    stantiate
    0.06
    æĤ¨å°±åı¯ä»¥
    0.06
    Activations Density 0.003%

    No Known Activations