© 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. 39912
    Prev
    Next
    INDEX
    Explanations

    renormalization and cancellation

    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
     Compr
    -0.08
    åªĽ
    -0.08
    å°
    -0.07
    èµĬ
    -0.07
    å§Ĺ
    -0.07
    伺
    -0.07
    æ··åIJĪåĬ¨åĬĽ
    -0.07
    обе
    -0.06
    xor
    -0.06
    keen
    -0.06
    POSITIVE LOGITS
     cancellation
    0.09
    Cancellation
    0.08
    ilos
    0.08
    åħ·ä½ĵéĹ®é¢ĺ
    0.08
     subtract
    0.07
     subtraction
    0.07
    uum
    0.07
     famously
    0.07
     crud
    0.07
     cancell
    0.07
    Activations Density 0.002%

    No Known Activations