© 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. 42962
    Prev
    Next
    INDEX
    Explanations

    sequence index notations like _i and _n

    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
    -0.07
    en
    -0.07
    athe
    -0.06
    ashi
    -0.06
    浩çĢļ
    -0.06
    ä¸įä¿¡
    -0.06
    åıįä¹ĭ
    -0.06
    orme
    -0.06
     h
    -0.06
    alley
    -0.06
    POSITIVE LOGITS
    ë§Īëĭ¤
    0.09
    åħĭ森
    0.08
    Each
    0.08
    venz
    0.08
    æĺ¯ä¸įåIJĮçļĦ
    0.08
     Rooney
    0.08
    each
    0.08
    arrer
    0.08
    çĻ¾åº¦äºij
    0.08
     themselves
    0.08
    Activations Density 0.010%

    No Known Activations