© 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. 57322
    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
    çĭ¬è§Ĵ
    -0.08
    czyk
    -0.07
    pled
    -0.07
    een
    -0.07
    way
    -0.07
    -regexp
    -0.07
    refour
    -0.07
    zej
    -0.07
    为éļ¾
    -0.07
    ä¸ĢçĤ¹
    -0.07
    POSITIVE LOGITS
    orney
    0.07
    æĥ³äºĨ解
    0.07
    ably
    0.07
     dah
    0.07
    بÛĮ
    0.07
    ersh
    0.07
     Fro
    0.06
    amework
    0.06
    ability
    0.06
    LIA
    0.06
    Activations Density 0.000%

    No Known Activations