© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23673
    Prev
    Next
    INDEX
    Explanations

    comparing or contrasting to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mage
    -0.09
    æĭ´
    -0.09
    akin
    -0.08
    -Americ
    -0.08
    gener
    -0.08
     Linden
    -0.08
    ä¾į
    -0.08
    inces
    -0.07
    åĴ
    -0.07
    ampa
    -0.07
    POSITIVE LOGITS
    æĬķèµĦ人
    0.12
    äºĨå¤ļå°ij
    0.10
    äºĨä¸įå°ij
    0.10
    广大群ä¼Ĺ
    0.09
    çļĦ家åºŃ
    0.09
    éĻµ
    0.09
    磶
    0.09
    ä»ĩ
    0.09
    çļĦä¸Ģ大
    0.08
     меÑħаниз
    0.08
    Activations Density 0.011%

    No Known Activations