© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7220
    Prev
    Next
    INDEX
    Explanations

    Category:

    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
    被æµıè§Ī
    -0.08
    quire
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹èĵĿåŃĹ
    -0.07
     اÙĦÙħج
    -0.07
    åħįè´¹åıijå¸ĥ
    -0.07
    colari
    -0.06
    ono
    -0.06
    Č
    -0.06
    POSITIVE LOGITS
    æ§ĥ
    0.08
    ÑĢÑĥÑĤ
    0.08
    å¸Į
    0.07
    ikko
    0.07
    iej
    0.07
    ï¼ļ%
    0.07
    .getRuntime
    0.07
    uyan
    0.06
    iesa
    0.06
    çł´å¤©
    0.06
    Activations Density 0.006%

    No Known Activations