© 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. 2791
    Prev
    Next
    INDEX
    Explanations

    group after start

    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
    æĵħ
    -0.08
    媲
    -0.08
     reason
    -0.07
    ä»¿ä½Ľæĺ¯
    -0.07
    mad
    -0.07
    以åıĬä¸İ
    -0.07
    æĢ»ä½ĵèĢĮè¨Ģ
    -0.07
    èµ°åĩºäºĨ
    -0.07
    ful
    -0.07
    inak
    -0.06
    POSITIVE LOGITS
    åįłäºĨ
    0.08
    onga
    0.07
    _component
    0.07
    åħ¶ä¸Ń
    0.07
    æľĢåIJİæĺ¯
    0.07
    contrib
    0.07
    .ReadOnly
    0.07
    _DEF
    0.07
    è´¡çĮ®
    0.07
    ÙĥÙĬ
    0.07
    Activations Density 0.279%

    No Known Activations