© 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. 28913
    Prev
    Next
    INDEX
    Explanations

    and lists

    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
    ÄĥÈĽ
    -0.08
    htable
    -0.08
    ogi
    -0.07
    áĥĿáĥł
    -0.07
    åıĮåŃIJ
    -0.07
    yr
    -0.07
    ORMAL
    -0.07
    INET
    -0.07
    ipop
    -0.07
    jeti
    -0.07
    POSITIVE LOGITS
    ä¸İåħ¶å®ĥ
    0.09
    åĴĮåħ¶å®ĥ
    0.09
     ÅŁi
    0.08
    åħ¶å®ĥ
    0.08
     اÙĦتÙī
    0.08
    ,and
    0.08
     etc
    0.08
    etc
    0.08
     colours
    0.08
     organisations
    0.08
    Activations Density 0.413%

    No Known Activations