© 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. 24395
    Prev
    Next
    INDEX
    Explanations

    numbers or code

    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
    ``
    -0.07
    оÑĢо
    -0.07
    ote
    -0.06
    мино
    -0.06
     ``
    -0.06
    MainThread
    -0.06
    orst
    -0.06
    iere
    -0.06
    verts
    -0.06
    å¤ĸåĮħ
    -0.06
    POSITIVE LOGITS
    éĢī项
    0.08
    éĢī项ä¸Ń
    0.08
     cruz
    0.08
    ayet
    0.08
    æķħéĢī
    0.08
    éģ¸éłħ
    0.08
    vir
    0.08
     Kanz
    0.08
    bek
    0.08
    essler
    0.08
    Activations Density 0.012%

    No Known Activations