© 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. 23180
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    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
    gettext
    -0.08
    (___
    -0.07
    riture
    -0.07
    impat
    -0.07
    aybe
    -0.07
    .Compiler
    -0.07
    ä¸įä¹±
    -0.07
    quete
    -0.07
    å¦ĤåĪĿ
    -0.07
    æ¶īåıĬçīĪæĿĥ
    -0.07
    POSITIVE LOGITS
    ól
    0.08
    ularity
    0.07
     ausdrücklich
    0.07
    Ø·
    0.06
     expressly
    0.06
    æĻĴ
    0.06
    å°±ä¸Ģå®ļè¦ģ
    0.06
    ÑĬ
    0.06
    гÑĢÑĥ
    0.06
     specifically
    0.06
    Activations Density 0.074%

    No Known Activations