© 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. 19542
    Prev
    Next
    INDEX
    Explanations

    oo or kk

    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
    fef
    -0.07
    uzzi
    -0.07
    ello
    -0.07
    stva
    -0.07
    vvm
    -0.07
    æĪİ
    -0.07
    为人
    -0.07
    cak
    -0.07
    bbc
    -0.07
    ürg
    -0.06
    POSITIVE LOGITS
    éĩijå®Ŀ
    0.07
    ÙĥÙĬÙħ
    0.07
    ule
    0.07
    zicht
    0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    0.07
    æ·ĩ
    0.06
    è´Ŀè´Ŀ
    0.06
    IMITER
    0.06
    olare
    0.06
    aters
    0.06
    Activations Density 0.004%

    No Known Activations