© 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. 64880
    Prev
    Next
    INDEX
    Explanations

    ====== separators

    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
    raphe
    -0.07
    hors
    -0.07
    åħŃæĪIJ
    -0.07
    ukke
    -0.07
    ued
    -0.07
    hier
    -0.07
    ruk
    -0.07
    åĿļ
    -0.07
    ä¹ĿæĪIJ
    -0.07
    itesse
    -0.07
    POSITIVE LOGITS
    nge
    0.08
    å¾ģéĢĶ
    0.08
    ngen
    0.07
    贴身
    0.07
    nder
    0.07
    éns
    0.07
    人家çļĦ
    0.07
    Past
    0.06
    éĻħ
    0.06
    yer
    0.06
    Activations Density 0.622%

    No Known Activations