© 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. 14777
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    à¸ĵà¹Į
    -0.07
    éĥ½ä¸į好
    -0.07
    家æľī
    -0.07
    å½ĵçĦ¶è¦ģ
    -0.07
    #"
    -0.07
    ]*(
    -0.07
    åįĥä¸ĩåĪ«
    -0.07
    kje
    -0.07
    åŃĺåľ¨æĦŁ
    -0.07
    ault
    -0.06
    POSITIVE LOGITS
    although
    0.07
    æĪĸæĺ¯
    0.07
    imately
    0.07
    åľ¨çĽ®åīį
    0.07
    è¶ħ
    0.07
    ä¸Ĭä½į
    0.06
    ç¢Į
    0.06
    åªĴ
    0.06
    èĢĮåľ¨
    0.06
     Whatsapp
    0.06
    Activations Density 0.504%

    No Known Activations