© 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. 56147
    Prev
    Next
    INDEX
    Explanations

    quotation marks, lists, strings

    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
    jenigen
    -0.14
    ìį¨
    -0.12
    hood
    -0.09
    psilon
    -0.09
    enni
    -0.09
    istic
    -0.09
    culares
    -0.09
    머ëĭĪ
    -0.09
    colari
    -0.09
    <|box_end|>
    -0.09
    POSITIVE LOGITS
    es
    0.17
    en
    0.14
    缸è¾ħ缸æĪIJ
    0.14
    er
    0.13
    i
    0.13
    ÏĤ
    0.12
    ä¼ĹæīĢåij¨çŁ¥
    0.12
    à¥ĩ
    0.12
    à¹Į
    0.12
    ar
    0.11
    Activations Density 0.068%

    No Known Activations