© 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. 4449
    Prev
    Next
    INDEX
    Explanations

    species names ending in -alis, -ia, -us

    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
    åIJİåĽł
    -0.07
    Âł
    -0.07
    åĪĨæĺİ
    -0.06
    uit
    -0.06
    akon
    -0.06
     lÃŃt
    -0.06
    æݨ移
    -0.06
     proven
    -0.06
    è¯»æľ¬
    -0.06
    cu
    -0.06
    POSITIVE LOGITS
    ocol
    0.08
    æĸ¯åħĭ
    0.08
    JsonValue
    0.08
    REP
    0.08
    -mobile
    0.08
    å¼ķéĩı
    0.07
    ['__
    0.07
    odont
    0.07
    -bre
    0.07
    å°ıé»Ħ
    0.07
    Activations Density 0.085%

    No Known Activations