© 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. 56615
    Prev
    Next
    INDEX
    Explanations

    configuration and initialization

    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
     Santi
    -0.07
    ç¸
    -0.07
    çĽ¸ä¿¡åľ¨
    -0.06
    หล
    -0.06
    اÙĦات
    -0.06
    åİĨæŶ
    -0.06
    æĥħæľī
    -0.06
    纨
    -0.06
    ffffffff
    -0.06
    gie
    -0.06
    POSITIVE LOGITS
    ä½łè¯´çļĦ
    0.08
    èĢĮä½ł
    0.07
    åī¯
    0.07
     Bow
    0.07
     securely
    0.07
    ayang
    0.07
    çĪ¬
    0.07
    æīĺ
    0.07
    å¼ł
    0.07
     nargin
    0.07
    Activations Density 0.100%

    No Known Activations