© 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. 56856
    Prev
    Next
    INDEX
    Explanations

    decoration

    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
    -0.10
    hood
    -0.09
    <|box_end|>
    -0.09
    ently
    -0.07
    á»ĭch
    -0.07
    napshot
    -0.07
    ledge
    -0.07
    wich
    -0.07
    ensee
    -0.07
    สà¹Į
    -0.06
    POSITIVE LOGITS
    åĵģçļĦ
    0.10
    ments
    0.08
    çĤ¹ç¼Ģ
    0.08
    teri
    0.08
    æīĵæī®
    0.08
    atively
    0.08
    reira
    0.07
    åłĤçļĩ
    0.07
    arily
    0.07
    飾
    0.07
    Activations Density 0.057%

    No Known Activations