© 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. 41274
    Prev
    Next
    INDEX
    Explanations

    4 beta

    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
    icago
    -0.08
    uhr
    -0.08
    fluence
    -0.07
    erule
    -0.07
    oney
    -0.07
    款
    -0.07
    /Register
    -0.07
    globals
    -0.07
    ameleon
    -0.07
    ifu
    -0.06
    POSITIVE LOGITS
    ÙĪرش
    0.07
    ä¹ĭ梦
    0.07
    ÙĪÙħاÙĨ
    0.07
    иÑģÑĤи
    0.07
    ings
    0.07
    pir
    0.06
    Bid
    0.06
    临æ²Ĥ
    0.06
    ä¸ŃéĺŁ
    0.06
    _numpy
    0.06
    Activations Density 0.002%

    No Known Activations