© 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. 7979
    Prev
    Next
    INDEX
    Explanations

    release, assessment, contest

    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
     fucking
    -0.07
    äºĮéĥİ
    -0.06
     pled
    -0.06
     bitch
    -0.06
    vel
    -0.06
    ilin
    -0.06
     freaking
    -0.06
    æĽ²
    -0.06
    طب
    -0.06
     lá»ĩ
    -0.06
    POSITIVE LOGITS
    æľĪçĶŁ
    0.08
    çĶŁåij½ç§ijåѦ
    0.08
    ä¹ĿéľĦ
    0.08
    å¤ļæł·çļĦ
    0.08
    лк
    0.08
    浦路
    0.07
    armi
    0.07
    داÙħ
    0.07
    unar
    0.07
    й
    0.07
    Activations Density 0.729%

    No Known Activations