© 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. 57299
    Prev
    Next
    INDEX
    Explanations

    need to solve/calculate

    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
    æĵħèĩª
    -0.07
    èĪįå¾Ĺ
    -0.07
    andola
    -0.06
    åĽ
    -0.06
    å·²æľī
    -0.06
     Tod
    -0.06
     Mod
    -0.06
    ailable
    -0.06
    并éĩĩåıĸ
    -0.06
     adul
    -0.06
    POSITIVE LOGITS
     möglichst
    0.10
    à¹ĥหà¹īà¹Ħà¸Ķà¹ī
    0.09
     urgently
    0.09
    çļĦæĺ¯
    0.08
    çļĦæĺ¯ä¸Ģ个
    0.08
    解åĨ³çļĦéĹ®é¢ĺ
    0.08
    .lu
    0.08
     urgente
    0.08
     ASAP
    0.08
     desesper
    0.08
    Activations Density 0.276%

    No Known Activations