© 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. 42501
    Prev
    Next
    INDEX
    Explanations

    phrase following "me" or "an"

    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
    ashed
    -0.09
    kest
    -0.08
    elper
    -0.08
    agak
    -0.08
    olec
    -0.08
    ãng
    -0.07
     hete
    -0.07
    ÑĢÑĬ
    -0.07
    ogr
    -0.07
    orp
    -0.07
    POSITIVE LOGITS
    åª
    0.08
    bul
    0.07
    Abstract
    0.07
    æ£
    0.07
    reon
    0.07
    inee
    0.07
    reen
    0.07
    ãĥŃãĥ¼ãĤº
    0.06
     Bul
    0.06
    æĽ´åºĶ该
    0.06
    Activations Density 0.006%

    No Known Activations