© 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. 27844
    Prev
    Next
    INDEX
    Explanations

    Star Wars trilogy

    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
     Gam
    -0.07
    éģįåıĬ
    -0.07
     Glock
    -0.07
     gam
    -0.06
    old
    -0.06
    人人
    -0.06
    糸
    -0.06
    èĹı
    -0.06
    åİŁ
    -0.06
     samba
    -0.06
    POSITIVE LOGITS
    бина
    0.08
    åģľæľº
    0.08
     ÑĢазÑĢе
    0.08
     separation
    0.08
     ÐĿовоÑģ
    0.08
    สà¸Ļิà¸Ĺ
    0.08
    TRL
    0.08
    fsp
    0.08
    pix
    0.08
     Pilot
    0.08
    Activations Density 0.019%

    No Known Activations