© 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. 27989
    Prev
    Next
    INDEX
    Explanations

    numbers after separators

    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
    RF
    -0.06
    aru
    -0.06
    à¸Ħรร
    -0.06
    rf
    -0.06
     Mercer
    -0.06
    èħ°æ¤İ
    -0.06
    夫å¦ĩ
    -0.06
     implode
    -0.06
    à»ī
    -0.06
    ä¸īäºĶ
    -0.06
    POSITIVE LOGITS
    ุà¸ķ
    0.09
    blia
    0.08
    isons
    0.08
     Rudd
    0.07
    ìĭľê¸°
    0.07
    agus
    0.07
    å»ºè®¾å·¥ä½ľ
    0.07
    åIJĪåIJĮæŶ
    0.07
    éĩįçĤ¹ä»»åĬ¡
    0.07
    Ñijд
    0.07
    Activations Density 0.033%

    No Known Activations