© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14933
    Prev
    Next
    INDEX
    Explanations

    conjugacy classes, packets defined

    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
     Zion
    -0.08
    mith
    -0.07
    orr
    -0.07
    é«ĺæĺİ
    -0.07
    ç«ĭäºİ
    -0.07
    hak
    -0.07
    antin
    -0.06
     buts
    -0.06
    ç§ijåѦçłĶ究éĻ¢
    -0.06
    boro
    -0.06
    POSITIVE LOGITS
    -groups
    0.07
    OID
    0.07
    omot
    0.07
    åĮºåĪ«
    0.07
    -group
    0.07
    åĽ¢
    0.07
    对称
    0.07
    ÑĢÑĥпп
    0.07
     distinguished
    0.07
    _identity
    0.07
    Activations Density 0.002%

    No Known Activations