© 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. 4299
    Prev
    Next
    INDEX
    Explanations

    topics and subjects

    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
    rod
    -0.07
    resso
    -0.06
    íĺ¼
    -0.06
    (s
    -0.06
    ï¸ı
    -0.06
    æľ¬èº«
    -0.06
    æī¿
    -0.06
    åĴ¬
    -0.06
     itself
    -0.06
    nea
    -0.06
    POSITIVE LOGITS
    ENDOR
    0.08
    adol
    0.08
    irian
    0.08
    -animate
    0.08
    akta
    0.07
    ãģ¨ãģĦãģ£ãģŁ
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    azu
    0.07
    leger
    0.07
     <![
    0.07
    Activations Density 0.367%

    No Known Activations