© 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. 48883
    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
    á»īnh
    -0.08
    am
    -0.08
    ä¸ĭè¿°
    -0.07
    usen
    -0.07
    å½ķ
    -0.07
    θÎŃ
    -0.07
    åīįè¿°
    -0.07
    ota
    -0.07
    edan
    -0.07
    elu
    -0.07
    POSITIVE LOGITS
    æīİåħĭ
    0.08
    ician
    0.07
    åĴĨ
    0.07
    åĪ°å¤©
    0.07
      ↵
    0.06
     newObj
    0.06
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.06
    á»ĩu
    0.06
    ä¸įå·²
    0.06
    trail
    0.06
    Activations Density 0.000%

    No Known Activations