© 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. 50773
    Prev
    Next
    INDEX
    Explanations

    declaration of variables

    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
    æĸ¯åħĭ
    -0.08
    ikum
    -0.08
    efore
    -0.07
    ÂŃs
    -0.07
    uelle
    -0.07
    antt
    -0.07
    ffet
    -0.06
    andes
    -0.06
    oul
    -0.06
    رÙħ
    -0.06
    POSITIVE LOGITS
    ListOf
    0.08
     yes
    0.07
    []}
    0.07
    为æݨåĬ¨
    0.07
     moo
    0.07
    çļĦåģļæ³ķ
    0.07
    chetta
    0.07
    edList
    0.06
     {}).
    0.06
    azos
    0.06
    Activations Density 0.006%

    No Known Activations