© 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. 32623
    Prev
    Next
    INDEX
    Explanations

    example lists or scenarios

    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
    éĴ©
    -0.07
     sovere
    -0.07
    åĭ¾
    -0.06
    udson
    -0.06
     Hanson
    -0.06
    2
    -0.06
     either
    -0.06
    éĶ¥
    -0.06
    åı¯çĶ±
    -0.06
    åĽ¾çĶ»
    -0.06
    POSITIVE LOGITS
    æī¹åĩĨçļĦé¡¹çĽ®
    0.09
     lautet
    0.09
    åĬłåħ¥æĪij们
    0.08
    tart
    0.08
    AtPath
    0.08
    å¦ĤæŃĮ
    0.08
    æľī以ä¸ĭ
    0.07
    AFX
    0.07
     ná»ĵng
    0.07
    اÙģات
    0.07
    Activations Density 0.008%

    No Known Activations