© 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. 38830
    Prev
    Next
    INDEX
    Explanations

    keep you

    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
    obel
    -0.07
     extensively
    -0.07
    åīįæīĢæľªæľīçļĦ
    -0.07
    orna
    -0.07
     outright
    -0.07
    à¹Ħà¸Ľà¹ģลà¹īว
    -0.07
    å¼Ģå§ĭ
    -0.07
    æĶ¹åıĺèĩªå·±
    -0.07
    finally
    -0.07
     впеÑĢвÑĭе
    -0.07
    POSITIVE LOGITS
    ä¿ĿæĮģåľ¨
    0.16
    Maint
    0.16
    ç»´æĮģåľ¨
    0.16
    ç»´æĮģ
    0.15
     maintained
    0.15
    ç¶ŃæĮģ
    0.15
     maintains
    0.14
     Maint
    0.14
     Maintain
    0.14
    maint
    0.14
    Activations Density 0.132%

    No Known Activations