© 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. 11025
    Prev
    Next
    INDEX
    Explanations

    early boost

    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
    åŃ¦ä¹łæĪIJ绩
    -0.07
    为主导
    -0.07
    éĢĤåIJĪäºİ
    -0.07
    wiki
    -0.07
    ory
    -0.07
    esity
    -0.06
    obody
    -0.06
    è§Ĩéķľ
    -0.06
    saan
    -0.06
    æľĢä½³
    -0.06
    POSITIVE LOGITS
    -checked
    0.09
     flawless
    0.09
    æĬ½æŁ¥
    0.08
     пÑĢовеÑĢки
    0.08
     пÑĢовеÑĢкÑĥ
    0.08
     Checked
    0.08
     questionable
    0.08
    çijķçĸµ
    0.08
    checking
    0.08
    å¤ļå¤Ħ
    0.08
    Activations Density 0.003%

    No Known Activations