© 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. 56110
    Prev
    Next
    INDEX
    Explanations

    frequency response

    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
    æĹ¥çĶµ
    -0.09
    åĨħçĶŁ
    -0.08
    å°Ķé¡¿
    -0.08
     massa
    -0.08
    versa
    -0.08
     ç§ģ
    -0.08
    缸åħ³æĸ°éĹ»
    -0.08
    ловиÑĩ
    -0.07
     createAction
    -0.07
    éĢīæĭ©éĢĤåIJĪèĩªå·±çļĦ
    -0.07
    POSITIVE LOGITS
    æ³¢çī¹
    0.09
    _dash
    0.07
     plot
    0.07
    acing
    0.07
    仪åĻ¨ä»ªè¡¨
    0.07
    åī¯æĢ»
    0.06
    æī«
    0.06
    åī¯æĢ»ç»ıçIJĨ
    0.06
    tr
    0.06
    egree
    0.06
    Activations Density 0.002%

    No Known Activations