© 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. 48384
    Prev
    Next
    INDEX
    Explanations

    agent that state without either of

    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¸Ģå¤ķ
    -0.09
    çİĸ
    -0.08
    ë¥
    -0.08
    ensee
    -0.08
    çļĦçIJĨæĥ³
    -0.07
    æĢİä¹ĪåĨĻ
    -0.07
    æĺĻ
    -0.07
    éĢĤå½ĵçļĦ
    -0.07
    mira
    -0.07
    åīįèĮħ
    -0.07
    POSITIVE LOGITS
    elden
    0.08
    åĪ°åºķæĺ¯
    0.08
    åı¯èĥ½æĢ§
    0.07
    èĹıåľ¨
    0.07
    abouts
    0.07
    ä¸Ģåħ±æľī
    0.07
    害
    0.07
     parmi
    0.07
     either
    0.07
    究竣æĺ¯
    0.07
    Activations Density 0.005%

    No Known Activations