© 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. 17228
    Prev
    Next
    INDEX
    Explanations

    Missing numbers

    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
    isk
    -0.07
    çĽ¸ä¿¡ä½ł
    -0.07
    rana
    -0.06
    ãĥ³ãĥĪ
    -0.06
    ecto
    -0.06
    械
    -0.06
    ä¸İä¼Ĺ
    -0.06
    arken
    -0.06
    æº
    -0.06
    ä½łåĸľæ¬¢
    -0.06
    POSITIVE LOGITS
    é¦
    0.08
    awi
    0.08
    é¹°
    0.07
    é¹Ń
    0.07
    paque
    0.07
    嵩
    0.07
    atson
    0.07
    anou
    0.07
    nom
    0.07
    alfa
    0.07
    Activations Density 0.008%

    No Known Activations