© 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. 42491
    Prev
    Next
    INDEX
    Explanations

    involved in

    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
    -scalable
    -0.08
    åIJįæĢĿ
    -0.07
    @js
    -0.07
    æĸ°åĨłèĤºçĤİçĸ«æĥħ
    -0.07
    odz
    -0.07
    .yy
    -0.06
    ulu
    -0.06
    variably
    -0.06
    æ¯ĭ庸置çĸij
    -0.06
    orz
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.12
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.10
    çļĦåħ¶ä»ĸ
    0.10
     comunque
    0.09
    带æĿ¥æĽ´å¤ļ
    0.08
     anyway
    0.07
     other
    0.07
    åģļå¾ĹæĽ´å¥½
    0.07
     دÛĮگرÛĮ
    0.07
     ändå
    0.07
    Activations Density 0.149%

    No Known Activations