© 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. 4808
    Prev
    Next
    INDEX
    Explanations

    new code

    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
    udeau
    -0.08
    rawat
    -0.07
    /docs
    -0.07
    }@
    -0.07
    à¹Īวย
    -0.07
    Scalars
    -0.07
    cuts
    -0.07
    odore
    -0.07
    :@
    -0.07
    аниÑĨ
    -0.07
    POSITIVE LOGITS
    [:,:,
    0.07
    ativ
    0.07
    ä»ĸèĩªå·±çļĦ
    0.06
     Rec
    0.06
    oc
    0.06
    oz
    0.06
    ison
    0.06
    anton
    0.06
    ç±³å°Ķ
    0.06
    بت
    0.06
    Activations Density 0.101%

    No Known Activations