© 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. 50824
    Prev
    Next
    INDEX
    Explanations

    comparison words like vs

    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
    lahan
    -0.08
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.08
    ucky
    -0.07
    åıĬ缸åħ³
    -0.07
    ardt
    -0.07
    æĬĸ
    -0.07
    çĪ±å°Ķ
    -0.06
    åıĬåħ¶ä»ĸ
    -0.06
    ác
    -0.06
    POSITIVE LOGITS
     vs
    0.10
     versus
    0.10
    vs
    0.09
    åĴĮå°ļ
    0.08
    -vs
    0.07
    åŀĭåĴĮ
    0.07
    _vs
    0.07
    èĢĮå¤į
    0.07
    åĴĮå¹³
    0.07
    ä¸İåĪĨæŀIJ
    0.07
    Activations Density 0.162%

    No Known Activations