© 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. 4108
    Prev
    Next
    INDEX
    Explanations

    or else conditions

    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
    éĤ£ä¹Īå¤ļ
    -0.08
     Sinatra
    -0.07
    ulp
    -0.07
    ìĹŃ
    -0.07
    alz
    -0.07
    è¿Ļä¹Īå¤ļ
    -0.07
    ([$
    -0.07
    符åIJĪæĿ¡ä»¶
    -0.07
    æĺ¯è¿Ļæł·
    -0.07
    è¯Ĩ
    -0.07
    POSITIVE LOGITS
    åīĶéĢı
    0.08
    Attrs
    0.07
    anges
    0.07
    æijĩäºĨ
    0.07
    ember
    0.07
    phans
    0.06
    æľªåıĸå¾Ĺ
    0.06
    ç¾İä¸Ń
    0.06
    anga
    0.06
    _was
    0.06
    Activations Density 0.037%

    No Known Activations