© 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. 24167
    Prev
    Next
    INDEX
    Explanations

    discriminants and twists

    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
    din
    -0.08
    ä¸įéĻIJ
    -0.07
     programmed
    -0.07
     Hamp
    -0.07
    为äºĨèĥ½
    -0.06
    人çļĦä¸ĢçĶŁ
    -0.06
    rán
    -0.06
    /rec
    -0.06
     Average
    -0.06
    墩
    -0.06
    POSITIVE LOGITS
     twists
    0.09
    ürt
    0.08
     twist
    0.08
    èµĦ
    0.08
    åħ¨åĽ½æĢ§
    0.07
     twisting
    0.07
     paranoia
    0.07
    .persist
    0.07
     Twist
    0.07
     gen
    0.07
    Activations Density 0.003%

    No Known Activations