© 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. 44102
    Prev
    Next
    INDEX
    Explanations

    errors and exceptions

    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
    è®´
    -0.08
    çĸijä¼¼è¿Ŀè§Ħ
    -0.07
    ampire
    -0.07
     REUTERS
    -0.07
    pora
    -0.06
     bals
    -0.06
     indeb
    -0.06
     dim
    -0.06
    åĵº
    -0.06
    elligence
    -0.06
    POSITIVE LOGITS
    Severity
    0.11
     severity
    0.11
     Severity
    0.10
    severity
    0.10
    Thrown
    0.09
    thrown
    0.08
    raised
    0.08
     thrown
    0.08
     винов
    0.08
    รุà¸Ļà¹ģรà¸ĩ
    0.08
    Activations Density 0.166%

    No Known Activations