© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15963
    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
    å±Ģéĥ¨
    -0.07
    nish
    -0.07
    æµ·æ£ł
    -0.07
    abili
    -0.07
    аем
    -0.06
    imei
    -0.06
    oco
    -0.06
    prak
    -0.06
    çī¹æľĹ
    -0.06
    iew
    -0.06
    POSITIVE LOGITS
    ä»ģ
    0.08
    åıĮåŃIJ
    0.07
    çĦ¶å¤§
    0.07
    åIJĥè¿ĩ
    0.07
     hon
    0.07
    ilter
    0.07
    leep
    0.06
    หà¸Ļ
    0.06
    ç¿©ç¿©
    0.06
    éĩijéĴĪ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.