© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21784
    Prev
    Next
    INDEX
    Explanations

    exercise or questions

    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
    ...
    -0.07
     Bomb
    -0.06
    oods
    -0.06
    éªij马
    -0.06
    å½ĵä¹ĭ
    -0.06
    ehlen
    -0.06
    ä¼ļèŃ°
    -0.06
    anager
    -0.05
    udd
    -0.05
    uddled
    -0.05
    POSITIVE LOGITS
    óle
    0.08
    
    0.08
    raje
    0.08
    ertino
    0.07
     **:**
    0.07
    rás
    0.07
     ÙģÙİØ¥
    0.07
     sportive
    0.07
    )':
    0.07
    "":
    0.07
    Activations Density 0.011%

    No Known Activations