© 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. 23216
    Prev
    Next
    INDEX
    Explanations

    differences and deviations

    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
    omu
    -0.07
    thinkable
    -0.07
    rray
    -0.07
    æ²³æ¹ĸ
    -0.07
    ä¹Łä¸įæĢķ
    -0.07
    ør
    -0.07
    lds
    -0.07
    ãĥĪãĥ©ãĥĸãĥ«
    -0.07
    é¹Ń
    -0.07
    ifold
    -0.07
    POSITIVE LOGITS
     rounding
    0.08
     unspecified
    0.08
     exact
    0.07
    精确
    0.07
     undisclosed
    0.07
    æīĢçĶ¨
    0.07
     imperfect
    0.07
    æŀķ
    0.07
     averaging
    0.07
    exact
    0.07
    Activations Density 0.019%

    No Known Activations