© 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. 11681
    Prev
    Next
    INDEX
    Explanations

    decimal places

    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
    OrCreate
    -0.08
    xn
    -0.08
    .collections
    -0.07
    åĭģ
    -0.07
    æľīçĹħ
    -0.07
    æĪ¿
    -0.07
    Õ²
    -0.07
    orce
    -0.07
    AndWait
    -0.07
    _REPLACE
    -0.06
    POSITIVE LOGITS
    ?,?,
    0.10
    çļĦä¸ī个
    0.08
    ä¸īç§į
    0.07
    اج
    0.07
    ä¸ī个
    0.07
    ä¸ī个éĺ¶æ®µ
    0.07
    ä¸īåĽĽ
    0.07
    amac
    0.07
    ä¸īèĢħ
    0.07
    è¿Ļä¸īç§į
    0.07
    Activations Density 0.144%

    No Known Activations