© 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. 47195
    Prev
    Next
    INDEX
    Explanations

    quotation marks and special characters

    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
    aja
    -0.07
    ombs
    -0.06
    epsi
    -0.06
    å°ĶèĴĻ
    -0.06
    enso
    -0.06
    eps
    -0.06
    éĤ£ä¹Ī容æĺĵ
    -0.06
     Pitt
    -0.05
    ome
    -0.05
    å®ģåĮº
    -0.05
    POSITIVE LOGITS
    życz
    0.07
    orris
    0.07
    isses
    0.07
    åij¼
    0.07
    å°ıåŃIJ
    0.07
    spel
    0.07
    ÑĢави
    0.07
    åIJĮ声
    0.07
    çĪĨç¬ij
    0.07
    åĽ½å®¶æ£®æŀĹåħ¬åĽŃ
    0.07
    Activations Density 0.015%

    No Known Activations