© 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. 15272
    Prev
    Next
    INDEX
    Explanations

    XML configuration data

    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
    èµ·æĿ¥åIJ§
    -0.07
    æĸĽ
    -0.07
    æ¶ķ
    -0.07
     orto
    -0.07
    ansch
    -0.07
    setLayout
    -0.07
    ç¬ijåĤ²
    -0.07
    çĺ©
    -0.07
     Cunning
    -0.07
    evoli
    -0.07
    POSITIVE LOGITS
    éģį
    0.07
    anguages
    0.07
    Âł
    0.06
    ucker
    0.06
    æŁ¥æŁ¥
    0.06
    éĿ¡
    0.06
    æĶ¯
    0.06
     Tiga
    0.06
     Âł
    0.06
    remen
    0.06
    Activations Density 0.015%

    No Known Activations