© 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. 30638
    Prev
    Next
    INDEX
    Explanations

    plans, statistics, observations

    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
    综åIJĪæĶ¹éĿ©
    -0.07
    elseif
    -0.07
    åIJĦåħ·
    -0.07
    æĺ¯éĤ£ä¹Ī
    -0.07
    åľŃ
    -0.07
    èıħ
    -0.07
    ยิà¸Ļ
    -0.06
    à¹Ģà¸Ĺà¹Īา
    -0.06
    elsif
    -0.06
    orit
    -0.06
    POSITIVE LOGITS
    åıĪä¸Ģ
    0.08
     Hint
    0.08
    ailability
    0.07
     besides
    0.07
     poleg
    0.07
    bes
    0.07
    家家
    0.07
    .observe
    0.07
    ä»Ģä¹ĪéĹ®é¢ĺ
    0.07
    èche
    0.07
    Activations Density 0.045%

    No Known Activations