© 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. 62437
    Prev
    Next
    INDEX
    Explanations

    histogram

    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
    .microsoft
    -0.10
    ãģ£ãģ±
    -0.08
    ordova
    -0.08
    Ắ
    -0.08
    çľīçľ¼
    -0.08
    ждÑĥÑİ
    -0.07
    <<<<<<<
    -0.07
    گار
    -0.07
    iare
    -0.07
    ä»İèĢĮ导èĩ´
    -0.07
    POSITIVE LOGITS
    èŁĢ
    0.08
    ึà¸ģ
    0.07
    opodob
    0.07
    æł·çļĦ
    0.07
    contri
    0.07
    uale
    0.06
    ály
    0.06
    ming
    0.06
    ayar
    0.06
    idine
    0.06
    Activations Density 0.026%

    No Known Activations