© 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. 49218
    Prev
    Next
    INDEX
    Explanations

    disc or disk followed by device or drive

    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
    irut
    -0.10
    toa
    -0.09
    est
    -0.08
    IGHL
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    swire
    -0.08
    à§įà¦ŀ
    -0.08
    ieber
    -0.08
    lyph
    -0.08
    ê²¹
    -0.08
    POSITIVE LOGITS
    ×IJ×ķת
    0.10
    ular
    0.08
    ature
    0.08
    es
    0.08
    ίο
    0.08
    ाय
    0.07
    atory
    0.07
    UNDER
    0.07
     sebelah
    0.07
    ar
    0.07
    Activations Density 0.056%

    No Known Activations