© 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. 23244
    Prev
    Next
    INDEX
    Explanations

    type annotations or declarations

    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
    γά
    -0.09
    çIJ³å¨ľ
    -0.08
    chau
    -0.08
    baugh
    -0.08
    :__
    -0.08
    ilst
    -0.08
    há
    -0.08
    èĥĨ
    -0.08
    èĨ½
    -0.08
    ERRU
    -0.08
    POSITIVE LOGITS
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.07
    lope
    0.07
    ä»Ģä¹Īåij¢
    0.07
    (
    0.07
    æĺ¯ä»Ģä¹Īåij¢
    0.06
     whatever
    0.06
     demol
    0.06
    ank
    0.06
     Ngh
    0.06
     (
    0.06
    Activations Density 0.003%

    No Known Activations