© 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. 32664
    Prev
    Next
    INDEX
    Explanations

    everything everywhere

    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
    为éĿŀ
    -0.07
    .vo
    -0.07
    ä¹°äºĨä¸Ģ
    -0.07
    ä¹Łä¸įå¿ħ
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    olge
    -0.07
    åºĶéĩĩåıĸ
    -0.07
    nga
    -0.07
    éĥ½ä¸į太
    -0.07
    æľ¬ä¾Ĩ
    -0.07
    POSITIVE LOGITS
    ä¸įåı¯æĪĸ缺
    0.13
    ä¸įåı¯æĽ¿ä»£
    0.11
    ä¸įåı¯ç¼ºå°ij
    0.11
    ä¸įåı¯æĪĸ缺çļĦ
    0.10
    éĩįè¦ģçļĦä½ľçĶ¨
    0.10
    çĶ¨å®ĥ
    0.10
     importance
    0.10
    举足
    0.10
    éĥ½ç¦»ä¸įå¼Ģ
    0.10
    éĩįè¦ģæĢ§
    0.10
    Activations Density 0.688%

    No Known Activations