© 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. 24061
    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
    _ci
    -0.08
    ordin
    -0.08
    ocs
    -0.07
    onesa
    -0.07
    esis
    -0.07
    èĩªè¡ĮæıIJä¾Ľ
    -0.07
    ihar
    -0.07
    rint
    -0.06
    æ´ŀåºŃ
    -0.06
     emer
    -0.06
    POSITIVE LOGITS
    ignon
    0.07
    ement
    0.07
    .RunWith
    0.07
    estig
    0.07
    ç±³å°Ķ
    0.07
    prima
    0.06
    noinspection
    0.06
    imap
    0.06
    çļĦçĥŃæĥħ
    0.06
     accurately
    0.06
    Activations Density 0.000%

    No Known Activations