© 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. 42964
    Prev
    Next
    INDEX
    Explanations

    collagens

    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
    çĤ¹ä»Ģä¹Ī
    -0.07
    çŁ
    -0.07
    Chooser
    -0.07
    Ø©
    -0.07
     Vors
    -0.07
     ih
    -0.07
    æľ¬æľŁ
    -0.06
    æ½ľä¼ı
    -0.06
    æľīæīĢ
    -0.06
    Except
    -0.06
    POSITIVE LOGITS
    ضÙħ
    0.07
    ä¸įçĿĢ
    0.06
    agg
    0.06
    æĹłç¼ĺ
    0.06
     essentially
    0.06
    ymb
    0.06
     ê²°êµŃ
    0.06
    kins
    0.06
     McL
    0.06
    /entities
    0.06
    Activations Density 0.006%

    No Known Activations