© 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. 48704
    Prev
    Next
    INDEX
    Explanations

    book formatting (Ed. pp.)

    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
    ä¸įæĺ¯å¾Ī好
    -0.07
    ä¸Ĭä¸Ģ次
    -0.07
    ¹Ħ
    -0.06
    alba
    -0.06
    å®Ī
    -0.06
    好æĸĩ
    -0.06
    acto
    -0.06
    ä¸ĭä¸Ģ级
    -0.06
    平平
    -0.06
     chan
    -0.06
    POSITIVE LOGITS
    ä¸Ńåħ¬
    0.08
    mær
    0.07
     vols
    0.07
    éĤģ
    0.07
    èľľæľĪ
    0.07
    çĥŃåįĸ
    0.07
    æ§ĭ
    0.07
    Ä«b
    0.07
    à¸ģà¹Į
    0.07
    涡轮å¢ŀåİĭ
    0.06
    Activations Density 0.036%

    No Known Activations