© 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. 43443
    Prev
    Next
    INDEX
    Explanations

    stage, during, bin, line, step

    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
    errer
    -0.07
    çĿ¹
    -0.07
    åĨłåIJį
    -0.07
    é«ĺå¯Ĩ
    -0.07
    aggio
    -0.07
    ä¸ļæĢģ
    -0.07
    emean
    -0.07
    cts
    -0.07
    ç»ĻæĪijä¸Ģ个
    -0.07
    _accessor
    -0.07
    POSITIVE LOGITS
     during
    0.09
    during
    0.09
    åħ³éĶ®çݯèĬĤ
    0.08
     During
    0.08
    During
    0.08
     أثÙĨاء
    0.08
    æŃ¥éª¤
    0.08
    åĪ°æľĢåIJİ
    0.08
    çݯèĬĤ
    0.08
     durante
    0.08
    Activations Density 0.308%

    No Known Activations