© 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. 19647
    Prev
    Next
    INDEX
    Explanations

    DNA followed by structural or functional terms

    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
    à¸ģารà¸ĵà¹Į
    -0.10
    ness
    -0.09
    ÑģÑı
    -0.09
    ett
    -0.08
    tlement
    -0.08
    ingly
    -0.07
    plier
    -0.07
    ãĢħãģ®
    -0.07
    稽
    -0.07
    gaard
    -0.07
    POSITIVE LOGITS
     Äijai
    0.09
    havn
    0.08
    arendra
    0.08
    arella
    0.07
    earch
    0.07
    asiun
    0.07
    wijs
    0.07
    igent
    0.07
    -binding
    0.07
    emus
    0.07
    Activations Density 0.058%

    No Known Activations