© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18008
    Prev
    Next
    INDEX
    Explanations

    each group

    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
    éĶ¦ä¸Ĭæ·»èĬ±
    -0.08
    escu
    -0.08
    egas
    -0.07
    epam
    -0.07
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.07
    zien
    -0.07
    ey
    -0.07
    [array
    -0.07
    ihn
    -0.07
    ArrayType
    -0.07
    POSITIVE LOGITS
    ëł¥
    0.07
    çļĦåĽŀçŃĶ
    0.07
     dinam
    0.07
    quen
    0.07
    alai
    0.07
    geben
    0.06
    çĻ½æ°´
    0.06
     valid
    0.06
    æĸ¹ä¾¿
    0.06
    iffe
    0.06
    Activations Density 0.002%

    No Known Activations