© 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. 18050
    Prev
    Next
    INDEX
    Explanations

    or policy

    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
    annage
    -0.07
     Heal
    -0.07
    ahead
    -0.07
    nowrap
    -0.06
     پاÛĮ
    -0.06
    isko
    -0.06
    åĩºæģ¯
    -0.06
    jú
    -0.06
    .wik
    -0.06
    éľĢè¦ģ注æĦı
    -0.06
    POSITIVE LOGITS
    å°±æĹłæ³ķ
    0.11
    æĹłä»¥
    0.10
    å°±ä¸įèĥ½
    0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    0.08
    zut
    0.07
    имÑĥ
    0.07
    åIJİæŀľ
    0.07
    å°±åıªèĥ½
    0.07
     nor
    0.07
    ä¹Łä¸įè¡Į
    0.07
    Activations Density 0.103%

    No Known Activations