© 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. 17231
    Prev
    Next
    INDEX
    Explanations

    amide derivatives or constituents

    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
    vens
    -0.08
    containers
    -0.07
    emberg
    -0.07
    reck
    -0.07
    碰
    -0.07
    entiel
    -0.07
    ëĭ¤ë©´
    -0.07
    queur
    -0.07
    etro
    -0.07
    ä¸įèĩ³
    -0.07
    POSITIVE LOGITS
    agine
    0.10
    ç»ĵæŀĦè°ĥæķ´
    0.08
    ç»ĵæŀĦ
    0.08
    ç»ĵæŀĦä¸Ń
    0.08
    amide
    0.08
    enna
    0.07
    è¾ĥéķ¿
    0.07
    urai
    0.07
    angered
    0.07
    endoza
    0.07
    Activations Density 0.015%

    No Known Activations