© 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. 44873
    Prev
    Next
    INDEX
    Explanations

    DisplayName, language codes, and names

    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
    èµĦ产交æĺĵ
    -0.08
    åĽ¾çŃī
    -0.07
    ettle
    -0.07
    åĵªåĦ¿
    -0.07
    etu
    -0.07
    ista
    -0.07
    èĢĮéĻį
    -0.07
    å®īåİ¿
    -0.07
    ongs
    -0.07
    istas
    -0.07
    POSITIVE LOGITS
    ierz
    0.08
    诸èijĽ
    0.06
     bes
    0.06
    æ¯Ľæ³½ä¸ľ
    0.06
     types
    0.06
    <!--[
    0.06
    uito
    0.06
    اغ
    0.06
    身临åħ¶å¢ĥ
    0.06
     symbol
    0.06
    Activations Density 0.010%

    No Known Activations