© 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. 52159
    Prev
    Next
    INDEX
    Explanations

    property in definition

    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
    èĩ
    -0.08
    burgh
    -0.07
    ELLE
    -0.07
    inete
    -0.07
    仲
    -0.07
    å¾¹
    -0.07
    appable
    -0.07
    jour
    -0.07
    è§Ħ
    -0.07
    cim
    -0.07
    POSITIVE LOGITS
     purported
    0.07
     intended
    0.07
     offered
    0.06
    çĪ·
    0.06
     strangely
    0.06
    çļĦéĹ®é¢ĺæĺ¯
    0.06
    emente
    0.06
     claims
    0.06
    Åij
    0.06
     tuning
    0.06
    Activations Density 0.008%

    No Known Activations