© 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. 41869
    Prev
    Next
    INDEX
    Explanations

    names followed by "("

    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
    _partial
    -0.08
    è¿ŀäºij
    -0.07
    zet
    -0.07
     setattr
    -0.07
     partial
    -0.07
    .partial
    -0.07
     Partial
    -0.07
    anke
    -0.07
     éner
    -0.06
    partial
    -0.06
    POSITIVE LOGITS
     بÙħعÙĨÙī
    0.11
    æĮĩçļĦæĺ¯
    0.10
     referring
    0.09
    à¹ĥà¸Ļà¸Ĺีà¹Ī
    0.09
     refers
    0.08
    æľ¬ä¹ī
    0.08
    ichtigkeit
    0.08
    åı¦
    0.08
    à¹ĥà¸Ļà¸Ħวาม
    0.08
    æĮĩçļĦ
    0.08
    Activations Density 0.231%

    No Known Activations