© 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. 8932
    Prev
    Next
    INDEX
    Explanations

    will be, newly, rewarded, won, Thanks again

    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
    åī
    -0.07
    ä¾ĭå¦Ĥ
    -0.07
    ÙĤØ©
    -0.07
     (?
    -0.07
    haar
    -0.06
    olling
    -0.06
     something
    -0.06
     (
    -0.06
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    -0.06
    æ°´ä¸Ń
    -0.06
    POSITIVE LOGITS
    reira
    0.08
    urv
    0.07
    hower
    0.07
    ä¸įçĶĺå¿ĥ
    0.07
    aney
    0.07
    uria
    0.07
    ündür
    0.07
    wania
    0.06
    asant
    0.06
    交éĢļè´¹
    0.06
    Activations Density 0.004%

    No Known Activations