© 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. 24580
    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
    éli
    -0.08
    akest
    -0.08
    anggar
    -0.07
    -0.07
    èĶ¼
    -0.07
    ekor
    -0.07
    irement
    -0.06
    è¯Ģ
    -0.06
    &apos
    -0.06
    aus
    -0.06
    POSITIVE LOGITS
    åĴĮéĹ®é¢ĺ
    0.06
    ä¸Ģ缮
    0.06
    ser
    0.06
    çļĦåİŁ
    0.06
    onese
    0.06
     sequer
    0.06
    æĸ°ä¹¡
    0.06
    åħĭçļĦ
    0.06
    caret
    0.06
    ä¸Ģå¤ľ
    0.06
    Activations Density 0.000%

    No Known Activations