© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44545
    Prev
    Next
    INDEX
    Explanations

    vary depending on

    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
    Negative Logits
    alon
    -0.08
    ê¸ī
    -0.08
    没æľīå¿ħè¦ģ
    -0.07
    伦
    -0.07
    _fault
    -0.07
    andom
    -0.07
    ression
    -0.07
    alom
    -0.07
    rand
    -0.07
    olon
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵè¦ģæ±Ĥ
    0.11
     depending
    0.08
     ÙħÙħÚ©ÙĨ
    0.08
     stricter
    0.08
    åıĸåĨ³äºİ
    0.08
    è¦ģçľĭ
    0.08
    restrict
    0.08
    åı¯èĥ½éľĢè¦ģ
    0.08
    depending
    0.08
    ä¹Łåı¯èĥ½
    0.08
    Activations Density 0.072%

    No Known Activations