© 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. 61714
    Prev
    Next
    INDEX
    Explanations

    potential gradient

    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
    izou
    -0.08
    ä»»ä½ķä¿Ŀè¯ģ
    -0.08
    ceaux
    -0.07
    æµ·ä¸ľ
    -0.07
     COPYING
    -0.07
    skal
    -0.07
    ذاء
    -0.07
    odob
    -0.07
    kre
    -0.07
     تعداد
    -0.07
    POSITIVE LOGITS
     opposes
    0.07
    çļĦå½¢æĪIJ
    0.07
     opposing
    0.07
     spontaneously
    0.07
     Voc
    0.07
    ä¿Ŀåį«
    0.07
    驹
    0.07
     pH
    0.07
     arises
    0.06
    çĽ¸ä¼ł
    0.06
    Activations Density 0.008%

    No Known Activations