© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55271
    Prev
    Next
    INDEX
    Explanations

    followed by then or is/released

    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
    çľĭåĩº
    -0.08
    zze
    -0.07
    iscos
    -0.06
    大äºĭ
    -0.06
    kirchen
    -0.06
    å¤Ń
    -0.06
    lech
    -0.06
    åħ¶çľŁå®ŀæĢ§
    -0.06
     coming
    -0.06
    èµ·çłģ
    -0.06
    POSITIVE LOGITS
     accordingly
    0.11
    åį³åı¯å®ĮæĪIJ
    0.09
     infine
    0.09
     finally
    0.08
    æĪij便
    0.08
    她便
    0.08
    inally
    0.08
     enfin
    0.08
    以ä¸Ĭå°±æĺ¯
    0.08
    缸åºĶçļĦ
    0.08
    Activations Density 0.047%

    No Known Activations