© 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. 1332
    Prev
    Next
    INDEX
    Explanations

    personal experiences and current states

    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
    VERBOSE
    -0.07
    ä»ĸ说
    -0.07
    Wr
    -0.07
     conto
    -0.07
    ิà¹īà¸ĩ
    -0.07
    å°±ç®ĹäºĨ
    -0.07
     dogs
    -0.06
    æľĢéĩįè¦ģçļĦ
    -0.06
    éŀŃ
    -0.06
    æľĢéĩįè¦ģ
    -0.06
    POSITIVE LOGITS
     likely
    0.11
     presumably
    0.10
     probably
    0.10
    ãģĬãģĿãĤīãģı
    0.09
    åı¯èĥ½æĺ¯
    0.09
    å¾Īåı¯èĥ½æĺ¯
    0.09
     Likely
    0.09
     pres
    0.08
     kemungkinan
    0.08
     probablemente
    0.08
    Activations Density 0.020%

    No Known Activations