© 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. 16904
    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
    åĪ«å¿ĺäºĨ
    -0.08
    illes
    -0.07
    ç·»
    -0.07
    大家åı¯ä»¥
    -0.06
     map
    -0.06
    .arguments
    -0.06
    quence
    -0.06
     Apart
    -0.06
    æİł
    -0.06
    arguments
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵéĹ®é¢ĺ
    0.08
    opil
    0.08
     λοι
    0.07
    idora
    0.07
    并æıIJä¾Ľ
    0.07
    ียà¸ĩ
    0.07
     vétér
    0.07
    wed
    0.07
     tehát
    0.07
    зÑĢе
    0.07
    Activations Density 0.000%

    No Known Activations