© 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. 63566
    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
    é¹¹
    -0.07
    ept
    -0.07
    ...”
    -0.06
    ä¹ĭåĪĥ
    -0.06
    éĿ¢æĹł
    -0.06
    rench
    -0.06
    人称
    -0.06
    quo
    -0.06
    IDD
    -0.06
    uja
    -0.06
    POSITIVE LOGITS
    maa
    0.08
    utors
    0.07
    ownt
    0.07
    æ¯Ķè¾ĥé«ĺ
    0.07
    ettori
    0.07
    _TILE
    0.06
    gaard
    0.06
     Cosmos
    0.06
    ä¸ĬäºĨ
    0.06
    tific
    0.06
    Activations Density 0.000%

    No Known Activations