© 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. 32372
    Prev
    Next
    INDEX
    Explanations

    roman numerals and numbers

    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
    éģ¥
    -0.07
    oz
    -0.07
    vo
    -0.07
    åĩłä¹İ
    -0.07
     Cra
    -0.07
    è¿ij
    -0.06
    åĮ¿åIJį
    -0.06
    áĥĶáĥĹ
    -0.06
    æ³Ľ
    -0.06
    è¶ħéĩį
    -0.06
    POSITIVE LOGITS
    åħ¶æŀĹ
    0.08
    uele
    0.07
    mane
    0.07
    ä½ķæĸ¹
    0.07
    ivain
    0.07
     Istitu
    0.07
    nad
    0.07
    ä¸Ģæĸ°çļĦ
    0.07
    áĢ±áĢ¬áĢĦáĢº
    0.07
    romise
    0.07
    Activations Density 0.049%

    No Known Activations