© 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. 29669
    Prev
    Next
    INDEX
    Explanations

    void/invalid contracts and judgments

    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
    æĺŁäºº
    -0.07
     uncompressed
    -0.07
    aga
    -0.07
    compressed
    -0.07
    nows
    -0.07
    WOR
    -0.07
    combe
    -0.07
    åķĨçļĦ
    -0.07
     compressed
    -0.07
    æıIJåīįåģļ好
    -0.07
    POSITIVE LOGITS
    çijķçĸµ
    0.11
     tainted
    0.09
    æĹłæķĪçļĦ
    0.09
     outright
    0.09
     invalid
    0.08
    INVALID
    0.08
    æĹłæķĪ
    0.08
    æ°ijäºĭè¡Į为
    0.08
    invalid
    0.08
     подлежиÑĤ
    0.08
    Activations Density 0.015%

    No Known Activations