© 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. 50822
    Prev
    Next
    INDEX
    Explanations

    phrase 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
    éĺ
    -0.08
    èĥ¤
    -0.07
    rible
    -0.07
    æĻ®ç½Ĺ
    -0.07
    spr
    -0.07
    ÑĢиÑģÑĤ
    -0.07
    LineStyle
    -0.06
    ried
    -0.06
    leston
    -0.06
    ILLE
    -0.06
    POSITIVE LOGITS
    à¹ĥหมà¹Īà¸Ĥà¸Ńà¸ĩ
    0.07
    临éŨ
    0.07
    olitik
    0.07
    itty
    0.07
    combe
    0.07
    qe
    0.07
    çłļ
    0.07
    uli
    0.07
    ä¹ĭäºİ
    0.07
    åĪĨæ°´
    0.06
    Activations Density 1.312%

    No Known Activations