© 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. 50028
    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
    CU
    -0.06
    enga
    -0.06
    âĢ¦
    -0.06
     assemblies
    -0.06
    ware
    -0.06
    éļ¾
    -0.06
    èĭıéĨĴ
    -0.06
    ffy
    -0.06
    大家
    -0.06
    ero
    -0.06
    POSITIVE LOGITS
    è®¤çľŁéĺħ读
    0.09
     (;;
    0.08
    建æĸ°
    0.08
    ÅĻeb
    0.08
    áĥĺáĥł
    0.08
    åĪĨå¤ĸ
    0.08
    presa
    0.07
    转载请
    0.07
    好ä¸į
    0.07
    æĥ³ä½ł
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.