© 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. 24935
    Prev
    Next
    INDEX
    Explanations

    thanks for comment

    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
     Lav
    -0.06
    æĺł
    -0.06
    Lav
    -0.06
     reta
    -0.06
    çĵ
    -0.06
    ä¸ĭ表
    -0.05
     Alta
    -0.05
    éĿĻçļĦ
    -0.05
    æ½ľåľ¨
    -0.05
     ar
    -0.05
    POSITIVE LOGITS
    above
    0.09
    å¦Ĥä¸Ĭ
    0.09
     described
    0.09
    -described
    0.09
    ļľ
    0.09
     above
    0.08
     outlined
    0.08
    Ïĥο
    0.08
     Above
    0.08
     Tiong
    0.08
    Activations Density 0.007%

    No Known Activations