© 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. 41344
    Prev
    Next
    INDEX
    Explanations

    avoid specific things

    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
     humane
    -0.08
     duly
    -0.07
    bane
    -0.07
    ÙĪغ
    -0.07
    åĪ«å¿ĺäºĨ
    -0.07
    åłĤåłĤ
    -0.07
    oppers
    -0.07
     improb
    -0.06
     suatu
    -0.06
    ä¿ĿæĬ¤æ³ķ
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ıçļĦ
    0.09
     overly
    0.09
    ä¸įè¦ģçĶ¨
    0.09
     excessive
    0.08
     use
    0.08
     unnecessary
    0.08
    use
    0.08
    ulum
    0.08
     attempts
    0.08
     reliance
    0.08
    Activations Density 0.050%

    No Known Activations