© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37689
    Prev
    Next
    INDEX
    Explanations

    summer morning

    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
    Negative Logits
    人æ°ijçļĦ
    -0.06
    çīµ
    -0.06
    æīĢå¤Ħ
    -0.06
    ellas
    -0.06
    olt
    -0.06
    å®Įæķ´åľ°
    -0.06
    å¿ĺ
    -0.06
    ÑģÑĤÑĮÑı
    -0.05
     Table
    -0.05
    quirrel
    -0.05
    POSITIVE LOGITS
    itor
    0.08
    abyte
    0.08
    á»ħ
    0.08
    èĬĭ
    0.08
    turut
    0.07
    euw
    0.07
    иÑĤоÑĢ
    0.07
    ä¹ĭ忧
    0.07
    trl
    0.07
    łíļ
    0.07
    Activations Density 0.003%

    No Known Activations