© 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. 25040
    Prev
    Next
    INDEX
    Explanations

    objects and achievements

    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
    çķ¥æľī
    -0.08
     Ñĩего
    -0.07
     nho
    -0.07
    纵çĦ¶
    -0.07
    åĪ°å¤´
    -0.07
    alba
    -0.07
    ivitÃł
    -0.07
    ulous
    -0.07
    åŃ°
    -0.07
    amica
    -0.07
    POSITIVE LOGITS
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    0.09
    ä¼¼çļĦ
    0.08
     exist
    0.08
    anted
    0.07
    çļĦ大åĬĽ
    0.07
    acu
    0.07
    áĥĵ
    0.07
     var
    0.06
    çİ°è¡ĮçļĦ
    0.06
    exist
    0.06
    Activations Density 0.440%

    No Known Activations