© 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. 57519
    Prev
    Next
    INDEX
    Explanations

    statistics and geography

    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
    æľ¬éĻ¢
    -0.08
    åıĪ以
    -0.07
     keh
    -0.07
    æł¹çļĦ
    -0.07
    -issue
    -0.07
    çݺ
    -0.07
    á»ĵng
    -0.07
     kep
    -0.06
    æĪĸå¤ļæĪĸå°ij
    -0.06
    椿
    -0.06
    POSITIVE LOGITS
    iya
    0.08
    egend
    0.07
    eria
    0.07
    osu
    0.06
    ixon
    0.06
     Piot
    0.06
    raud
    0.06
    пÑĢоÑĩем
    0.06
    equip
    0.06
     bref
    0.06
    Activations Density 0.330%

    No Known Activations