© 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. 7508
    Prev
    Next
    INDEX
    Explanations

    related to pricing, salt, UI, photos, countries, physiological, network, element, manager

    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
     penn
    -0.07
    å¼ģ
    -0.07
    åīį身
    -0.07
    ä¸įæį¢
    -0.06
    fce
    -0.06
    IBLE
    -0.06
    件ä¸Ń
    -0.06
    æŁ¿
    -0.06
    ialized
    -0.06
    ible
    -0.06
    POSITIVE LOGITS
    -focused
    0.10
    -themed
    0.10
    -related
    0.09
    ä¸ŃåĽ½ç½ij
    0.08
    anson
    0.08
    -oriented
    0.08
    uit
    0.08
    -specific
    0.07
     Getter
    0.07
     represented
    0.07
    Activations Density 0.483%

    No Known Activations