© 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. 46816
    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
    Âł
    -0.08
    çĽ¸ä¿¡èĩªå·±
    -0.07
    å¢
    -0.07
     classe
    -0.07
    å±
    -0.06
    产éĺ¶çº§
    -0.06
    åıĤèĢĥèµĦæĸĻ
    -0.06
    è¿Ĥ
    -0.06
    å®ŀä½ĵ
    -0.06
    åĶ¯çĭ¬
    -0.06
    POSITIVE LOGITS
    åı¯ç¼ĸç¨ĭ
    0.08
    ish
    0.08
    ä¹IJä¸ļ
    0.08
    -ish
    0.07
    Exact
    0.07
    ostal
    0.07
    енÑĮ
    0.07
    arget
    0.07
    çݲçıij
    0.07
     exact
    0.07
    Activations Density 0.000%

    No Known Activations