© 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. 20111
    Prev
    Next
    INDEX
    Explanations

    numeric lists or 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
    ters
    -0.08
    amina
    -0.08
    çĶļèĩ³æĺ¯
    -0.07
    my
    -0.07
    iers
    -0.07
    aner
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    å°½æĥħçļĦ
    -0.07
    ers
    -0.06
    ("."
    -0.06
    POSITIVE LOGITS
    çĽ¸ä¿¡ä½ł
    0.07
    ently
    0.07
    éĻĮ
    0.07
    ัà¸ĩ
    0.07
    âĸ¶
    0.07
    кÑĥпа
    0.06
    DidLoad
    0.06
    Ñģмо
    0.06
    驾车
    0.06
    γÏĩ
    0.06
    Activations Density 0.074%

    No Known Activations