© 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. 20041
    Prev
    Next
    INDEX
    Explanations

    graph, GR

    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
    åħ¶æīĢ
    -0.08
    ?!
    -0.07
    éĩĮåİ»
    -0.07
    à§įত
    -0.07
     Tran
    -0.06
    iland
    -0.06
    bih
    -0.06
    渡
    -0.06
    æ·Ĩ
    -0.06
    uby
    -0.06
    POSITIVE LOGITS
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    ================================================================
    0.07
    ï¼¾
    0.07
    occa
    0.07
     @}
    0.07
    rw
    0.07
    å¹²éĥ¨ç¾¤ä¼Ĺ
    0.07
    ((__
    0.07
     simplest
    0.07
    ordinator
    0.07
    Activations Density 0.025%

    No Known Activations