© 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. 24527
    Prev
    Next
    INDEX
    Explanations

    subgroup

    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
    rex
    -0.07
    对çĶ¨æĪ·
    -0.07
    æīĵãģ¡
    -0.07
    iero
    -0.07
    æľīä½Ļ
    -0.07
    iac
    -0.07
    ä¹Łè®¸ä¼ļ
    -0.06
    éĢ¢
    -0.06
    ÙĬÙĨØ©
    -0.06
    ä¸ĭæĮ«
    -0.06
    POSITIVE LOGITS
    unload
    0.08
    äºĮçŃī
    0.08
    å®ĩ
    0.08
    æĬĹåĩ»
    0.07
     нали
    0.07
    éĻį
    0.07
    山寨
    0.07
     subgroup
    0.07
    åįĬæķ°
    0.07
    ä¸īçŃī
    0.07
    Activations Density 0.006%

    No Known Activations