© 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. 19814
    Prev
    Next
    INDEX
    Explanations

    anti-

    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
    ãĤĪãģĨãģª
    -0.09
    à¥į
    -0.08
    ettings
    -0.08
    ochen
    -0.08
    ians
    -0.08
    lah
    -0.08
    indel
    -0.08
    aux
    -0.07
    æĶ¾çŁ¢
    -0.07
    ر
    -0.07
    POSITIVE LOGITS
    Ø©
    0.15
    ation
    0.13
    ness
    0.11
    entication
    0.11
    ed
    0.10
    ção
    0.09
    ਣ
    0.09
    ение
    0.08
    erring
    0.08
    zung
    0.08
    Activations Density 0.027%

    No Known Activations