© 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. 745
    Prev
    Next
    INDEX
    Explanations

    take a

    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
    ysel
    -0.07
    å·²çĶ±
    -0.07
    iggio
    -0.06
    çĤ¹ãģ¯
    -0.06
     deselect
    -0.06
    Sent
    -0.06
    aye
    -0.06
    è¶ĬæĹ©
    -0.06
    对æīĢ
    -0.06
    åĩŃåĢŁ
    -0.06
    POSITIVE LOGITS
     into
    0.10
    à¹Ħวà¹īà¹ĥà¸Ļ
    0.10
    èĢĮ代ä¹ĭ
    0.09
    设å¤ĩè¿Ľè¡Į
    0.08
     onto
    0.08
    into
    0.08
    ä¿¡æģ¯è¿Ľè¡Į
    0.08
    à¹ĥหà¹īà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    åľ¨èº«ä¸Ĭ
    0.08
     Into
    0.07
    Activations Density 1.058%

    No Known Activations