© 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. 57575
    Prev
    Next
    INDEX
    Explanations

    citations and statistics

    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
    çĸij
    -0.06
    æľīä¸Ģ次
    -0.06
     practices
    -0.06
    ļ
    -0.06
    åºķ
    -0.06
    iba
    -0.06
    rop
    -0.06
    dda
    -0.06
    Âł
    -0.05
     Jab
    -0.05
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.09
    è°ĥæŁ¥æĺ¾ç¤º
    0.08
     Lev
    0.08
    é¾Ļèħ¾
    0.07
    举æĬ¥
    0.07
    è¿ĩ好
    0.07
    andes
    0.07
     miÄĻd
    0.07
    vias
    0.07
    idot
    0.07
    Activations Density 0.009%

    No Known Activations