© 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. 57425
    Prev
    Next
    INDEX
    Explanations

    throughout, elsewhere, everyone

    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
     spectral
    -0.07
    ohl
    -0.07
    affle
    -0.06
    /spec
    -0.06
     accurately
    -0.06
    ekar
    -0.06
    åĩłç»ı
    -0.06
    ooled
    -0.06
    lund
    -0.06
     kolek
    -0.06
    POSITIVE LOGITS
    æĹłå¤Ħä¸įåľ¨
    0.17
    éļıå¤Ħ
    0.16
     Everywhere
    0.14
    éļıæŶéļıåľ°
    0.14
    æĹłæŶæĹłåĪ»
    0.13
    å¤Ħå¤Ħ
    0.13
     everywhere
    0.13
    éļıå¤Ħåı¯è§ģ
    0.12
     wherever
    0.12
    æĹ¥å¸¸çĶŁæ´»
    0.12
    Activations Density 0.105%

    No Known Activations