© 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. 20147
    Prev
    Next
    INDEX
    Explanations

    isotope, isomers, isabella, isohydry, is, as is

    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
    à¥į
    -0.09
    ä¼ģä¸ļ
    -0.08
    ãģĦ
    -0.08
    æľīèĩ´
    -0.08
    entes
    -0.07
    µ
    -0.07
    ¹
    -0.07
    eschi
    -0.07
    ìĬ¤ëŁ¬ìļ´
    -0.07
    ždy
    -0.07
    POSITIVE LOGITS
    otope
    0.14
    olation
    0.13
    abella
    0.11
    olated
    0.11
    omorphic
    0.10
    mert
    0.10
    olate
    0.10
    ermann
    0.09
    aac
    0.09
    ván
    0.09
    Activations Density 0.244%

    No Known Activations