© 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. 50778
    Prev
    Next
    INDEX
    Explanations

    specified desired their expected

    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
    yata
    -0.08
    byname
    -0.08
    èĻ½çĦ¶æĺ¯
    -0.08
    èıģ
    -0.08
    æĺİæĺİæĺ¯
    -0.07
    รà¸Ļ
    -0.07
    osse
    -0.07
    åħīåįİ
    -0.07
    cza
    -0.07
    æĸ°æµªç½ij
    -0.07
    POSITIVE LOGITS
     specified
    0.07
     expected
    0.07
     respective
    0.07
     their
    0.07
    specified
    0.07
     desired
    0.07
    åħ¶çī¹å¾ģ
    0.07
     greatest
    0.06
     guessed
    0.06
     theirs
    0.06
    Activations Density 0.156%

    No Known Activations