© 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. 48894
    Prev
    Next
    INDEX
    Explanations

    and punctuation

    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
    ikle
    -0.08
    ahi
    -0.08
    hofer
    -0.07
    æĢľ
    -0.07
    UBLE
    -0.07
    hors
    -0.07
    oop
    -0.07
    ulen
    -0.07
    pil
    -0.07
    UIL
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.10
     where
    0.09
    å¼ıä¸Ń
    0.08
     wobei
    0.08
     waarbij
    0.08
    where
    0.08
    emente
    0.07
     où
    0.07
     где
    0.07
    é¼ĵèµ·
    0.07
    Activations Density 0.026%

    No Known Activations