© 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. 20109
    Prev
    Next
    INDEX
    Explanations

    department of Physics

    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
    .nasa
    -0.09
    åd
    -0.09
    纨
    -0.09
    ighed
    -0.08
    év
    -0.08
     Merke
    -0.08
    ibaldi
    -0.08
    ä¹İåħ¶
    -0.08
    åħ¬ç§¯éĩij贷款
    -0.08
    সà§įয
    -0.08
    POSITIVE LOGITS
    erce
    0.07
     nouvel
    0.07
    ä¸ĢéŨ
    0.07
    æĪij们ä¼ļ尽快
    0.07
    ors
    0.06
    æĸ¹æ³ķä¸İ
    0.06
     Gn
    0.06
    iri
    0.06
    éĻĮ
    0.06
    ahn
    0.06
    Activations Density 0.236%

    No Known Activations