© 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. 8802
    Prev
    Next
    INDEX
    Explanations

    (OH) groups, chemical formulas, hydroxyapatite

    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
    es
    -0.10
    et
    -0.08
    Ø©
    -0.08
    it
    -0.07
    ar
    -0.07
    as
    -0.07
    at
    -0.06
    an
    -0.06
    The
    -0.06
    (
    -0.06
    POSITIVE LOGITS
    åĮĸçī©
    0.09
     fitte
    0.08
    laden
    0.08
    åı¯æ¢¦
    0.08
    enthal
    0.08
    ÏįÏĦε
    0.08
    entai
    0.08
    én
    0.08
    UMO
    0.08
     sâm
    0.08
    Activations Density 0.001%

    No Known Activations