© 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. 22544
    Prev
    Next
    INDEX
    Explanations

    establishment or amendment

    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
    zan
    -0.08
    æ¸ĭ
    -0.07
    æĬ¢åħĪ
    -0.07
    éłIJåijĬ
    -0.07
    zá
    -0.07
    å¼ĥæĿĥ
    -0.07
    won
    -0.07
    Ïĥκο
    -0.07
    udz
    -0.07
    cn
    -0.07
    POSITIVE LOGITS
    缴åĪ°
    0.11
    缴èĩ³
    0.10
     until
    0.10
    until
    0.09
    ä½ĨéļıçĿĢ
    0.09
    缴åĪ°çİ°åľ¨
    0.08
    ä¸Ģ缴åĪ°
    0.08
     Until
    0.08
    Until
    0.08
    _until
    0.08
    Activations Density 0.417%

    No Known Activations