© 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. 65168
    Prev
    Next
    INDEX
    Explanations

    confidential or secret information

    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
    ystone
    -0.08
    ãĤ¤ãĥī
    -0.08
    ecca
    -0.08
     underrated
    -0.07
     trag
    -0.07
    æłĩæľ¬
    -0.07
    isma
    -0.07
    ulla
    -0.07
    биÑĤи
    -0.07
    Obsolete
    -0.07
    POSITIVE LOGITS
    ä¿Ŀå¯Ĩ
    0.18
    ç§ĺå¯Ĩ
    0.17
     confidential
    0.16
    çļĦç§ĺå¯Ĩ
    0.16
    æľºå¯Ĩ
    0.15
     secret
    0.15
     secrecy
    0.15
     secrets
    0.15
    éĢıéľ²
    0.14
    secret
    0.14
    Activations Density 0.314%

    No Known Activations