© 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. 55581
    Prev
    Next
    INDEX
    Explanations

    specialties and miscellaneous

    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
    ç¸
    -0.06
    opy
    -0.06
    éĥ
    -0.05
    åį¦
    -0.05
     markings
    -0.05
    æııè¿°
    -0.05
    æĬĦ
    -0.05
    accio
    -0.05
    羣çIJĨ
    -0.05
    -0.05
    POSITIVE LOGITS
    ãĤĴ対象
    0.11
    ä¸ĢèĪ¬é¡¹çĽ®
    0.11
    主è¦ģéĴĪ对
    0.10
     lucrative
    0.09
    åħ¨èĪ¬
    0.09
    åĽĽç±»
    0.09
     specialty
    0.09
    éĩįçĤ¹æĺ¯
    0.09
     specialties
    0.09
     miscellaneous
    0.09
    Activations Density 0.474%

    No Known Activations