© 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. 30490
    Prev
    Next
    INDEX
    Explanations

    cheese with hamburger

    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
    Unchecked
    -0.09
    steen
    -0.09
    符
    -0.09
    DBObject
    -0.09
    èķ¤
    -0.09
    ÑıÑħ
    -0.09
    á»ĩm
    -0.09
    èĦ¾æ°Ķ
    -0.08
    çļĦæĦŁåıĹ
    -0.08
    红èĮ¶
    -0.08
    POSITIVE LOGITS
     Tango
    0.09
    æ½®
    0.09
    еÑģÑģ
    0.09
     пок
    0.09
     Erot
    0.09
    åĽŀåIJĪ
    0.09
    æĪĺçģ«
    0.08
    ddl
    0.08
     chees
    0.08
    èŀį
    0.08
    Activations Density 0.044%

    No Known Activations