© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29824
    Prev
    Next
    INDEX
    Explanations

    ester compounds

    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
    fter
    -0.08
    emaker
    -0.08
    arching
    -0.07
    æĨĶ
    -0.07
    atrix
    -0.07
    ilib
    -0.07
    åIJĴ
    -0.07
    torno
    -0.07
    è¯Ľ
    -0.07
    echa
    -0.07
    POSITIVE LOGITS
    ãģĽãĤĵ
    0.08
    nton
    0.07
    mented
    0.07
    menta
    0.07
    berry
    0.07
    éķ¿é£İ
    0.07
    ä¸Ģæ°Ķ
    0.06
    innen
    0.06
     mÆ°Æ¡i
    0.06
    atro
    0.06
    Activations Density 0.020%

    No Known Activations