© 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. 4669
    Prev
    Next
    INDEX
    Explanations

    greeting or introductory phrase

    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
    à¹Ģลย
    -0.06
    -0.06
    åĥ»
    -0.06
    çļĩ
    -0.06
     proph
    -0.06
     âĢ¦
    -0.06
    ëIJĺì§Ģ
    -0.06
     بغ
    -0.06
    Configure
    -0.05
     Proph
    -0.05
    POSITIVE LOGITS
    ç©į
    0.10
    åĬłåħ³æ³¨
    0.08
    积
    0.08
    VarChar
    0.08
    á»ĵng
    0.08
    onse
    0.08
    edora
    0.08
    маÑħ
    0.08
    enor
    0.08
    elem
    0.08
    Activations Density 0.002%

    No Known Activations