© 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. 42152
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and abbreviations like HS, HB, HT

    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
    weit
    -0.07
    entifier
    -0.07
    entication
    -0.07
    ÏĤ
    -0.06
    ypse
    -0.06
    rysler
    -0.06
    ãĥ£
    -0.06
    fei
    -0.06
    кÑĢаÑĤно
    -0.06
    itecture
    -0.06
    POSITIVE LOGITS
    htags
    0.08
    ól
    0.08
    chenken
    0.08
    žo
    0.07
    ikipedia
    0.07
    OwnProperty
    0.07
    ç»į
    0.07
    chsel
    0.07
    èĸĩ
    0.07
    سÙĬر
    0.07
    Activations Density 0.006%

    No Known Activations