© 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. 29334
    Prev
    Next
    INDEX
    Explanations

    anhydride / anhydrous / hydrides

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    getter
    -0.07
    asso
    -0.07
    ayakan
    -0.07
    inalg
    -0.07
    кви
    -0.07
    asu
    -0.07
    apphire
    -0.07
    asl
    -0.07
    pecified
    -0.07
    POSITIVE LOGITS
    ÑģÑı
    0.09
    ого
    0.09
    rous
    0.09
    ä¸Ģ度çļĦ
    0.08
    elsing
    0.08
    ufe
    0.08
    reas
    0.07
    iram
    0.07
    enticate
    0.07
    stry
    0.07
    Activations Density 0.004%

    No Known Activations