© 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. 27695
    Prev
    Next
    INDEX
    Explanations

    experiment 1

    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
    ine
    -0.07
    åĪ«çļĦ
    -0.06
    anes
    -0.06
    ä¸įè¿ĩ
    -0.06
    à¹Īà¸Ńย
    -0.06
    inne
    -0.06
    åħ¶æīĢ
    -0.06
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    -0.06
    å®ĥæīĢ
    -0.06
     here
    -0.06
    POSITIVE LOGITS
    éĹ®åĮ»çĶŁ
    0.08
    ergus
    0.08
     ():
    0.08
     EXTR
    0.08
    åıijçĶŁäºİ
    0.08
    èµ°ä¸Ģèµ°
    0.07
    oric
    0.07
    oweit
    0.07
     Extr
    0.07
    gart
    0.07
    Activations Density 0.026%

    No Known Activations