© 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. 30781
    Prev
    Next
    INDEX
    Explanations

    sale finalized

    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
    еÑģÑģ
    -0.07
    å¾·ç½Ĺ
    -0.06
    æĢ»åĢ¼
    -0.06
    .qq
    -0.06
    illi
    -0.06
    uyan
    -0.06
    ccount
    -0.06
    æīĭæľºçīĪ
    -0.06
    çļĦ人们
    -0.06
     foss
    -0.06
    POSITIVE LOGITS
    åħ¶åľ¨
    0.10
    åħ¶ä¸İ
    0.10
    对åħ¶
    0.09
    åħ¶è¡Į为
    0.09
    åħ¶èĩªçĦ¶
    0.09
    ä»İåħ¶
    0.09
     its
    0.09
    åĽłåħ¶
    0.09
    ä¿Ŀè¯ģåħ¶
    0.09
    以åħ¶
    0.09
    Activations Density 0.536%

    No Known Activations