© 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. 34189
    Prev
    Next
    INDEX
    Explanations

    confidential information or secrets

    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
    å¯Ľ
    -0.08
    ä¸IJ
    -0.08
    ATCH
    -0.07
    bac
    -0.07
     isempty
    -0.07
    ÑģÑĤÑĬ
    -0.07
    alani
    -0.07
     angesch
    -0.07
    eku
    -0.07
    irkan
    -0.07
    POSITIVE LOGITS
    ä¿Ŀå¯Ĩ
    0.15
    æ³Ħéľ²
    0.15
    åķĨä¸ļç§ĺå¯Ĩ
    0.14
    æľºå¯Ĩ
    0.13
    æ³Ħ
    0.13
     confidentiality
    0.13
    ç§ĺå¯Ĩ
    0.12
     confidential
    0.12
    çļĦç§ĺå¯Ĩ
    0.11
     Confidential
    0.11
    Activations Density 0.045%

    No Known Activations