© 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. 28271
    Prev
    Next
    INDEX
    Explanations

    Seems like

    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
    åį´ä¾ĿçĦ¶
    -0.10
    åį´ä¸įæĺ¯
    -0.09
    ä½ĨæĦ¿
    -0.08
    éĤ£ä»ĸ
    -0.08
    åħĭéļ¾
    -0.08
    åį´å§ĭç»Ī
    -0.08
    å¦Ĥæŀľä»ĸ们
    -0.08
    ä½Ĩ她
    -0.08
    æĢİä¹ĪåĨĻ
    -0.08
    ught
    -0.08
    POSITIVE LOGITS
     there
    0.12
    æīĢæľīçļĦ
    0.10
    there
    0.09
    è¿Ļæĺ¯
    0.09
    มีà¸ģาร
    0.08
     they
    0.08
    æīĢæľī
    0.08
     ÙĩÙĨاÙĥ
    0.08
    è¿Ļæĺ¯ä¸Ģ个
    0.08
    this
    0.08
    Activations Density 0.044%

    No Known Activations