© 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. 49396
    Prev
    Next
    INDEX
    Explanations

    editorial additions

    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
     misd
    -0.07
    讨åİĮ
    -0.07
    è··
    -0.07
    culp
    -0.07
    åıĬåħ¶åºĶçĶ¨
    -0.07
    eced
    -0.07
    _then
    -0.07
    è¿«
    -0.07
    elta
    -0.07
    schuld
    -0.07
    POSITIVE LOGITS
    æѤå¤Ħ
    0.08
    é¢ĸ
    0.08
     here
    0.08
     added
    0.08
    unn
    0.07
    为éĩįçĤ¹
    0.07
    è¿ĻéĩĮæĺ¯
    0.07
    è°ĥæķ´ä¸º
    0.07
    æĶ¹æĪIJ
    0.07
    Added
    0.07
    Activations Density 0.027%

    No Known Activations