© 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. 62414
    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
    jene
    -0.09
    ׼×Ļ
    -0.08
    /rs
    -0.08
    éĿŀå¿ħè¦ģ
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
     Prive
    -0.07
    anus
    -0.07
    åIJĦ家
    -0.07
    frieden
    -0.07
    ìa
    -0.07
    POSITIVE LOGITS
    åĨĻåĩºäºĨ
    0.07
    “
    0.06
    ()
    0.06
    对æĪijåĽ½
    0.06
    åıĪ称
    0.06
     writings
    0.06
    aug
    0.06
    被称为
    0.06
    w
    0.06
    被èªī为
    0.06
    Activations Density 0.000%

    No Known Activations