© 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. 49786
    Prev
    Next
    INDEX
    Explanations

    prime factors

    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
    æī£
    -0.08
    reno
    -0.08
    åį³çĶ¨
    -0.07
    xDF
    -0.07
    è¢«æŁ¥
    -0.07
    ÙĪرت
    -0.07
    èµģ
    -0.07
    deo
    -0.07
    æīĢçĶ¨
    -0.07
    æīĢ使çĶ¨çļĦ
    -0.07
    POSITIVE LOGITS
    åħ¨éĥ¨çļĦ
    0.10
    åĶ¯ä¸ĢçļĦ
    0.08
    ä»ħæľīçļĦ
    0.08
    åħ¨éĥ¨
    0.08
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.07
    ä¸Ģåħ±æľī
    0.07
    åĪĹ表
    0.07
    çļĦåħ¨éĥ¨
    0.07
    ä¸Ģç½ij
    0.07
     aside
    0.07
    Activations Density 0.014%

    No Known Activations