© 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. 13005
    Prev
    Next
    INDEX
    Explanations

    clue, differences, nuances, mentioned

    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
    Sab
    -0.08
     Helf
    -0.07
    èĽĬ
    -0.07
    sab
    -0.07
    áf
    -0.07
    colar
    -0.07
     haus
    -0.07
    accompagn
    -0.07
    urato
    -0.07
    ursed
    -0.07
    POSITIVE LOGITS
     discre
    0.07
    ç¡®å®ŀ
    0.07
    纾
    0.07
     ÐĶей
    0.07
     differences
    0.06
    建åĨĽ
    0.06
    ãĤĭãĤĪãģĨãģ«
    0.06
     nuances
    0.06
    ç¸
    0.06
    Indeed
    0.06
    Activations Density 0.021%

    No Known Activations