© 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. 26867
    Prev
    Next
    INDEX
    Explanations

    serializing to JSON

    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
    ninger
    -0.08
    åĩĢ
    -0.07
    physical
    -0.07
     cancelling
    -0.07
    è°ĥæݧ
    -0.07
    gart
    -0.06
    catch
    -0.06
    èĩªåĬ¨æݧåĪ¶
    -0.06
    é¦Ĵ
    -0.06
     Physical
    -0.06
    POSITIVE LOGITS
    zet
    0.07
    æľīéĴ±
    0.07
    æ®ĸæ°ij
    0.07
    делки
    0.06
    atian
    0.06
    åģļ人
    0.06
    TableCell
    0.06
    人称
    0.06
    render
    0.06
    转åĮĸ
    0.06
    Activations Density 0.049%

    No Known Activations