© 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. 25024
    Prev
    Next
    INDEX
    Explanations

    numbers and underscores

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ifah
    -0.07
     Aut
    -0.06
    ister
    -0.06
    bat
    -0.06
    æī«åľ°
    -0.06
    æīĢåģļ
    -0.06
    allen
    -0.05
     aut
    -0.05
    WP
    -0.05
      ↵
    -0.05
    POSITIVE LOGITS
    åIJİåįĬ
    0.08
    äºĨä¸ĢæĶ¯
    0.08
    élet
    0.07
    åIJİèĢħ
    0.07
    ÏĩÏħ
    0.07
    θο
    0.07
    å°ı人
    0.07
    足
    0.07
    åľ¨æľĢåIJİ
    0.07
    禾
    0.07
    Activations Density 0.378%

    No Known Activations