© 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. 23175
    Prev
    Next
    INDEX
    Explanations

    This is

    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
    æľ±åħĥ
    -0.08
     differently
    -0.08
    åħ®
    -0.07
    éĤ£æł·
    -0.07
    lock
    -0.07
    è¿Ļæł·åģļ
    -0.07
    artige
    -0.07
     able
    -0.07
    ä¸įå°ı
    -0.07
    ä¸įäºĨå¤ļä¹ħ
    -0.07
    POSITIVE LOGITS
    orem
    0.09
    家ä¼Ļ
    0.08
     adalah
    0.08
    ossi
    0.08
    顾åIJįæĢĿä¹ī
    0.08
    jenigen
    0.08
     is
    0.07
     ÙĩÙħاÙĨ
    0.07
    ê±°
    0.07
    åį«çĶŁç»Ħç»ĩ
    0.07
    Activations Density 0.067%

    No Known Activations