© 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. 42119
    Prev
    Next
    INDEX
    Explanations

    variable names `i`, `n`, `j` often followed by `,` or `=`

    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
    èĸª
    -0.08
    ottima
    -0.08
    +#
    -0.07
    èĮģ壮
    -0.07
    baÅŁ
    -0.07
    ÑģаÑĤа
    -0.07
    缴æİ¥æĪĸ
    -0.07
    elia
    -0.06
    ä¸įèĭŁ
    -0.06
    æĹłæĤĶ
    -0.06
    POSITIVE LOGITS
    çĻ»å½ķæŁ¥çľĭ
    0.07
    ยà¹Į
    0.07
    æķijäºĨ
    0.07
    alles
    0.07
    yed
    0.06
     resta
    0.06
    ilik
    0.06
     Compos
    0.06
    åݲ
    0.06
    allest
    0.06
    Activations Density 0.006%

    No Known Activations