© 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. 40853
    Prev
    Next
    INDEX
    Explanations

    prime factors or arithmetic operations

    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
    黯çĦ¶
    -0.09
    Ð¢Ðł
    -0.08
    oyer
    -0.08
    并ä¸įé«ĺ
    -0.08
    æīİåħĭ
    -0.08
    edata
    -0.07
     :(
    -0.07
    边走边
    -0.07
    annes
    -0.07
    å¾Ģä¸ĭ
    -0.07
    POSITIVE LOGITS
     boosted
    0.08
     boosts
    0.08
     boosting
    0.08
    æĪIJæŃ£
    0.08
    解æĶ¾
    0.08
    缸åıįçļĦ
    0.08
    é¢łåĢĴ
    0.07
    åıį转
    0.07
    boost
    0.07
     compliments
    0.07
    Activations Density 0.047%

    No Known Activations