© 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. 30952
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    åı¯å¯¹
    -0.06
    ä¿Ń
    -0.06
    ä¾ł
    -0.06
    æĦŁæŁĵäºĨ
    -0.06
    åĮĸä½ľ
    -0.06
    æ´»åĬ¨è¿ĩç¨ĭ
    -0.06
    angler
    -0.06
    ÙİاÙĨ
    -0.06
    kost
    -0.06
    nde
    -0.06
    POSITIVE LOGITS
    voli
    0.07
    _while
    0.07
    vento
    0.07
    رÙĬض
    0.07
    çĺ
    0.07
     McCabe
    0.07
    Äįov
    0.07
    à¤Łà¤ķ
    0.07
    oeff
    0.07
    éĢĨ
    0.07
    Activations Density 0.001%

    No Known Activations