© 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. 46531
    Prev
    Next
    INDEX
    Explanations

    X followed by common suffixes

    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
    ìį¨
    -0.20
    ation
    -0.13
    phine
    -0.12
    ized
    -0.11
    ally
    -0.10
    خداÙħ
    -0.09
    iable
    -0.09
    ormais
    -0.09
    <|box_end|>
    -0.09
    ated
    -0.09
    POSITIVE LOGITS
    en
    0.16
    s
    0.14
    es
    0.14
    à¥ĩ
    0.14
    е
    0.14
    er
    0.14
    enticate
    0.14
    à¹Į
    0.13
    ing
    0.13
    ive
    0.12
    Activations Density 0.064%

    No Known Activations