© 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. 26428
    Prev
    Next
    INDEX
    Explanations

    Hunt

    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
    ä¸įæŃ£
    -0.06
    aum
    -0.06
    åŃľ
    -0.06
    èijĹ
    -0.06
     gatherings
    -0.06
    æĹłæĿĥ
    -0.06
    imini
    -0.06
    ustom
    -0.06
    èģļä¼ļ
    -0.06
    çŁĹ
    -0.06
    POSITIVE LOGITS
     underrated
    0.09
    lla
    0.08
    çĬ¶æĢģçļĦ
    0.08
     titulaire
    0.08
    aliza
    0.08
    èħ¾è®¯å¾®åįļ
    0.08
    wych
    0.08
     ÑĥÑĢо
    0.07
    embe
    0.07
    zza
    0.07
    Activations Density 0.441%

    No Known Activations