© 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. 19484
    Prev
    Next
    INDEX
    Explanations

    locations and names

    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
    æĹ¢çĦ¶å¦ĤæѤ
    -0.07
    åĨįä¸ī
    -0.06
    åĩ¹åĩ¸
    -0.06
     getX
    -0.06
    è¬Ĥ
    -0.06
    è´Ńåľ°
    -0.06
    æĪijåĢĴ
    -0.06
    çŁ
    -0.06
    à¹ī
    -0.06
    类似
    -0.06
    POSITIVE LOGITS
    esp
    0.07
    _typeof
    0.07
    cano
    0.07
     plats
    0.07
    ursal
    0.07
    urse
    0.06
    asen
    0.06
     verm
    0.06
    /chart
    0.06
    arno
    0.06
    Activations Density 0.009%

    No Known Activations