© 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. 28051
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    åIJİèĢħ
    -0.09
    vence
    -0.08
    apon
    -0.08
    åIJĪåIJĮæŶ
    -0.08
    illen
    -0.07
    éĥ½ä¸įæĥ³
    -0.07
     @}
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    apork
    -0.07
    اÙģÙĬØ©
    -0.07
    POSITIVE LOGITS
    ãģĺãĤģ
    0.07
    ÄŁ
    0.07
    ÑĮÑİ
    0.07
    èĢĺ
    0.07
    æ·±
    0.07
    zell
    0.06
    峨çľī
    0.06
    cts
    0.06
     vi
    0.06
    UTH
    0.06
    Activations Density 0.545%

    No Known Activations