© 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. 57382
    Prev
    Next
    INDEX
    Explanations

    remainder when divided by

    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
    hq
    -0.08
     neighbouring
    -0.08
    注
    -0.07
    º¼
    -0.07
    å®ĥè¿ĺ
    -0.07
    it
    -0.07
    éĤ»è¿ij
    -0.07
    aldi
    -0.07
     neighbours
    -0.07
    为äºĨèĥ½
    -0.07
    POSITIVE LOGITS
    kau
    0.07
    åħ·æľī以ä¸ĭ
    0.07
    ynet
    0.07
    å°Ĩä¸Ģ个
    0.07
    è¦ģæĮīçħ§
    0.07
    ropp
    0.07
    æīĢæľīåĨħ容
    0.06
    _face
    0.06
    æĪijåIJĹ
    0.06
    øb
    0.06
    Activations Density 0.045%

    No Known Activations