© 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. 2337
    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
    ficit
    -0.10
    订éĺħä¸ĵæłı
    -0.10
    ÏĦÎŃ
    -0.08
    äºĶ天
    -0.08
    åľ°éģĵ
    -0.08
    转载æĪĸå¼ķçĶ¨
    -0.07
    ordion
    -0.07
    thern
    -0.07
    çīĪæĿĥåĿĩ
    -0.07
    转载èĩ³
    -0.07
    POSITIVE LOGITS
    å±ħæĺĵ
    0.08
    yman
    0.07
    anch
    0.06
    çŀ°
    0.06
    ç¼ħæĢĢ
    0.06
    lau
    0.06
    åĴĮ第äºĮ
    0.06
     Gon
    0.06
     I
    0.05
    ¶
    0.05
    Activations Density 0.000%

    No Known Activations