© 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. 19918
    Prev
    Next
    INDEX
    Explanations

    discontinued, less, necessary

    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
    Lit
    -0.08
    æīįä¼ļ
    -0.07
    éģ¿è®©
    -0.07
     Lit
    -0.07
    æīįæľĥ
    -0.07
    ä¸į说
    -0.07
    rett
    -0.06
    æĤ¶
    -0.06
     Rather
    -0.06
    verg
    -0.06
    POSITIVE LOGITS
     trusting
    0.10
     trust
    0.10
     Trust
    0.10
    ä¹Łè¡Į
    0.09
    åıªè¦ģèĥ½
    0.09
     risky
    0.09
    åľ¨ä¿Ŀè¯ģ
    0.09
    trust
    0.09
    åīįæıIJ
    0.09
     trusts
    0.09
    Activations Density 0.188%

    No Known Activations