© 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. 2250
    Prev
    Next
    INDEX
    Explanations

    hydroxyl radical or OH

    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
    ially
    -0.11
     halnya
    -0.08
    ÑģÑĮ
    -0.08
    ìļĶ
    -0.08
    Ùĭ
    -0.08
    ãģ¾ãģ¾
    -0.07
    à¸ģà¹Į
    -0.07
    uner
    -0.07
    ible
    -0.07
    semb
    -0.07
    POSITIVE LOGITS
    alloween
    0.10
    essian
    0.09
    aupt
    0.09
    ancock
    0.09
    usband
    0.08
    olland
    0.08
    aupts
    0.08
    undred
    0.08
    solete
    0.08
    iggins
    0.08
    Activations Density 0.012%

    No Known Activations