© 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. 28236
    Prev
    Next
    INDEX
    Explanations

    number of / than

    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
    icona
    -0.08
    Ïģμο
    -0.08
    ä»·æł¼åIJĪçIJĨ
    -0.08
    身为
    -0.08
    _cutoff
    -0.08
    anh
    -0.07
     Principe
    -0.07
    ovin
    -0.07
     à¤ķाà¤Ĥà¤Ĺ
    -0.07
    èĻ¹
    -0.07
    POSITIVE LOGITS
     arithmetic
    0.07
     radic
    0.07
    ä¸Ģæķ°
    0.06
     minu
    0.06
     orally
    0.06
    à¹Ī
    0.06
    æĶ¹æİī
    0.06
    äºĭæĥħçļĦ
    0.06
     numbers
    0.06
    builder
    0.06
    Activations Density 0.020%

    No Known Activations