© 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. 40560
    Prev
    Next
    INDEX
    Explanations

    appellant

    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
    åĽŀ访
    -0.07
    çļĦ综åIJĪ
    -0.07
    ÅĽl
    -0.07
    综åIJĪèĥ½åĬĽ
    -0.07
    æ²½
    -0.06
    alker
    -0.06
    opup
    -0.06
    imeline
    -0.06
    åİŁåĪĽä½ľåĵģ
    -0.06
    Å¡ov
    -0.06
    POSITIVE LOGITS
    çłĶ
    0.08
    azÄĥ
    0.07
     Dynam
    0.07
    áŀĻ
    0.07
    implemented
    0.07
    åĸľéĹ»
    0.07
     Extract
    0.07
    æijĨåľ¨
    0.06
    extract
    0.06
    -query
    0.06
    Activations Density 0.001%

    No Known Activations