© 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. 34901
    Prev
    Next
    INDEX
    Explanations

    percentages or fractions

    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
    eza
    -0.07
    åıł
    -0.06
    å®ĥä¹Ł
    -0.06
    &id
    -0.06
    ient
    -0.06
     numer
    -0.06
    inaire
    -0.06
    çĶ¨å®ĥ
    -0.06
    elles
    -0.06
    trag
    -0.06
    POSITIVE LOGITS
    obia
    0.07
    <|box_end|>
    0.07
    æŀĹ天
    0.07
    룩
    0.07
    ãģ£ãģıãĤĬ
    0.07
    询
    0.07
    !--
    0.07
    å¢ħ
    0.07
    onton
    0.07
    мÑĸн
    0.07
    Activations Density 0.091%

    No Known Activations