© 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. 7827
    Prev
    Next
    INDEX
    Explanations

    `/a` URLs

    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
    æĤ´
    -0.10
     Istitu
    -0.10
    ardy
    -0.09
    -animate
    -0.09
    .ua
    -0.09
    tura
    -0.09
    ministra
    -0.09
    æĪ·æĻĵ
    -0.09
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.09
    èĢ³é¼»
    -0.09
    POSITIVE LOGITS
    0.07
    ·
    0.07
    ↵
    0.07
    (
    0.06
    âĢ¢
    0.06
    PR
    0.06
     &
    0.06
     —
    0.06
    7
    0.06
    8
    0.06
    Activations Density 0.008%

    No Known Activations