© 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. 21056
    Prev
    Next
    INDEX
    Explanations

    detection and monitoring

    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
    ä¸Ģä½ľ
    -0.08
    latin
    -0.08
    ê±°
    -0.08
    adou
    -0.08
    _creation
    -0.07
    landers
    -0.07
    éĢīæĭ©éĢĤåIJĪèĩªå·±çļĦ
    -0.07
    嬢
    -0.07
     ÙĦتÙĥÙĪÙĨ
    -0.07
    arez
    -0.07
    POSITIVE LOGITS
     detection
    0.11
     Detection
    0.09
     Detect
    0.09
    Detection
    0.09
     detecting
    0.09
     accurately
    0.09
     detect
    0.08
    detect
    0.08
    çļĦæ£Ģæµĭ
    0.08
    åĩĨç¡®çļĦ
    0.08
    Activations Density 0.254%

    No Known Activations