© 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. 40864
    Prev
    Next
    INDEX
    Explanations

    affiliation and address

    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
     amsterdam
    -0.08
     Jeb
    -0.07
    anan
    -0.07
    osso
    -0.07
    ,top
    -0.06
    ÑģÑģеÑĢ
    -0.06
    첩
    -0.06
    sier
    -0.06
    å°Ĩæľī
    -0.06
    æĪĸå°Ĩ
    -0.06
    POSITIVE LOGITS
    主è¦ģä»İäºĭ
    0.08
    æĿ¥ç¨¿
    0.07
     gr
    0.07
    主è¦ģ为
    0.07
     affiliation
    0.07
     affili
    0.07
     bang
    0.07
    -aff
    0.06
     affiliate
    0.06
    деÑĢж
    0.06
    Activations Density 0.389%

    No Known Activations