© 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. 25842
    Prev
    Next
    INDEX
    Explanations

    listing numerical sequences

    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
    tz
    -0.06
    '
    -0.06
    ä¸įèĩªè§ī
    -0.06
    度ãģ«
    -0.05
    "
    -0.05
    pun
    -0.05
    upu
    -0.05
    Ù°
    -0.05
    VEL
    -0.05
    çļĦ好
    -0.05
    POSITIVE LOGITS
    oseb
    0.09
    ĥĿ
    0.08
    æĺ¨å¤ľ
    0.08
    incar
    0.08
    evin
    0.08
    acar
    0.08
    ãĥ¼ãĥĬ
    0.08
    icara
    0.08
    Äĩen
    0.08
     etc
    0.08
    Activations Density 0.009%

    No Known Activations