© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12139
    Prev
    Next
    INDEX
    Explanations

    already, June, maturity, passports, talks

    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
    Not in Any Lists

    No Comments

    Negative Logits
    é½IJ
    -0.07
    virtual
    -0.07
    trar
    -0.07
    iless
    -0.07
     dÃłnh
    -0.06
     Pup
    -0.06
     convention
    -0.06
    elow
    -0.06
    åĪ¶å¤ĩ
    -0.06
     domest
    -0.06
    POSITIVE LOGITS
     Already
    0.12
     already
    0.12
    already
    0.10
    åĪļæīį
    0.10
    å·²ç¶ĵ
    0.09
    æĪij们已ç»ı
    0.09
    å·²ç»ı
    0.09
    å·²
    0.09
     déjÃł
    0.09
     باÙĦÙģعÙĦ
    0.09
    Activations Density 0.246%

    No Known Activations