© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    availability statement

    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
     cso
    -0.07
    éģ
    -0.07
    ÙĪÛĮ
    -0.07
    æ¯ıä¸Ģ个ç»ĨèĬĤ
    -0.07
     Dorm
    -0.07
    æľªå®Į
    -0.07
    Discover
    -0.07
    é«ĺçħ§
    -0.06
    æī¾æĪij
    -0.06
    ÙĤÙĤ
    -0.06
    POSITIVE LOGITS
    acias
    0.07
     plages
    0.07
    kena
    0.07
    olia
    0.07
    ARB
    0.06
    erait
    0.06
    :none
    0.06
    chemes
    0.06
    å·¥ç¨ĭåѦéĻ¢
    0.06
     nÃło
    0.06
    Activations Density 0.262%

    No Known Activations