© 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. 49163
    Prev
    Next
    INDEX
    Explanations

    legal rights and condition

    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
    åĮķ
    -0.08
    æĹħ游线路
    -0.07
    æł¡åĽŃéĩĮ
    -0.07
    antik
    -0.07
    orz
    -0.07
    mane
    -0.07
    åĬŀåħ¬å®¤éĩĮ
    -0.07
    æīįèĥ½ä¿Ŀè¯ģ
    -0.07
    agnes
    -0.07
    oport
    -0.07
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģ项
    0.10
    ä¸įåľ¨
    0.09
    ä¸įå±ŀäºİ
    0.09
    æ¯Ķçħ§
    0.09
    åĪĹåħ¥
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    被è§Ĩ为
    0.08
    ä¸Ģæ¦Ĥ
    0.08
    å±ŀäºİ
    0.08
     rient
    0.08
    Activations Density 0.036%

    No Known Activations