© 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. 15528
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    reno
    -0.10
    à¹ģà¸Ļะ
    -0.09
    upro
    -0.09
    doÄŁan
    -0.09
    alte
    -0.08
    println
    -0.08
    truc
    -0.08
    clave
    -0.08
    ////////////////////////////////////////////////////////
    -0.08
    erima
    -0.08
    POSITIVE LOGITS
    åı¯å¾ª
    0.12
    fully
    0.09
    æĢ§çļĦ
    0.08
    ingly
    0.08
    ously
    0.08
    æĢ§åľ°
    0.07
    æĶ¯éħį
    0.07
    z
    0.07
    æĢ§
    0.07
    åĴĮçī¹çĤ¹
    0.07
    Activations Density 0.000%

    No Known Activations