© 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. 38772
    Prev
    Next
    INDEX
    Explanations

    prime factors of 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
    adop
    -0.08
    sker
    -0.07
    æ´ĹåĩĢ
    -0.07
     revan
    -0.07
    æ´Ĺ
    -0.07
    çĻ¾å§ĵç½ij
    -0.07
    esus
    -0.07
    æĿ
    -0.07
    istro
    -0.07
    ave
    -0.07
    POSITIVE LOGITS
    件
    0.08
    件çļĦ
    0.07
    ãģ«ãģĭ
    0.07
     defens
    0.06
    .emit
    0.06
    ovi
    0.06
     uncertain
    0.06
    è°¨éĺ²
    0.06
    æľĢæĸ°è¯Ħ论
    0.06
    iteten
    0.06
    Activations Density 0.008%

    No Known Activations