© 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. 58295
    Prev
    Next
    INDEX
    Explanations

    last or final occurrence

    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
    æ¢ħæŀĹ
    -0.07
    å²Ń
    -0.07
    ucle
    -0.07
     Vale
    -0.06
     Me
    -0.06
    /logs
    -0.06
    cut
    -0.06
    letter
    -0.06
    instance
    -0.06
     cut
    -0.06
    POSITIVE LOGITS
    åĪ°çĽ®åīį为æŃ¢
    0.12
    æļĤæŶ
    0.10
    è¿Ħä»Ĭ为æŃ¢
    0.10
    åĪĿæŃ¥
    0.09
     finora
    0.09
    æĹ©æľŁ
    0.08
    é¦ĸæľŁ
    0.08
    åĪĿæľŁ
    0.08
    æĪªèĩ³çĽ®åīį
    0.08
     till
    0.08
    Activations Density 0.311%

    No Known Activations