© 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. 55603
    Prev
    Next
    INDEX
    Explanations

    code and markup structure

    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
    ¹
    -0.06
    马è¹Ħ
    -0.06
    cott
    -0.06
    à±įà°µ
    -0.05
    isky
    -0.05
    _CREAT
    -0.05
    <|endoftext|>
    -0.05
    éĩij森
    -0.05
    çİ®
    -0.05
    以ä¸ĭ
    -0.05
    POSITIVE LOGITS
    ĵ¨
    0.08
    å¾ĢæľŁåĽŀ顾
    0.08
    ä¹ĭåŃIJ
    0.08
    меÑĢи
    0.08
    ÐĿовоÑģÑĤи
    0.08
    æľ¬å¸ĸ
    0.08
    å¾ĢæľŁç²¾å½©
    0.08
    **”
    0.08
    º¼
    0.08
    odem
    0.08
    Activations Density 0.344%

    No Known Activations