© 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. 1721
    Prev
    Next
    INDEX
    Explanations

    author emails

    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
    łĢ
    -0.06
    rier
    -0.06
    ĵĺ
    -0.06
     Nok
    -0.06
     zare
    -0.06
    ê°ģ
    -0.06
    à§ĥ
    -0.06
     dyn
    -0.05
    ç»Ŀ
    -0.05
    ä¸ĥ彩
    -0.05
    POSITIVE LOGITS
    æ¢ħæŀĹ
    0.09
    ç³Ł
    0.08
    unga
    0.08
    å°ıèĬĤ
    0.08
    xo
    0.08
    epass
    0.07
    è´Łè´£å¯¹
    0.07
    ignes
    0.07
    ffects
    0.07
    vus
    0.07
    Activations Density 0.002%

    No Known Activations