© 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. 53508
    Prev
    Next
    INDEX
    Explanations

    Bloomberg, Anderson, Duffer, Brothers

    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
    less
    -0.10
    æ°ĶåĬ¿
    -0.10
    ÑıÑī
    -0.09
    èıģ
    -0.09
    apult
    -0.09
    èĥ½åĬĽåĴĮ
    -0.09
    ино
    -0.09
    apat
    -0.09
    ÑĢеÑģ
    -0.09
    å·®ä¸įå¤ļ
    -0.08
    POSITIVE LOGITS
    失è°ĥ
    0.09
    çłĶåĪ¤
    0.08
    éļĽ
    0.08
    è¿Ħ
    0.08
    æģģ
    0.08
    аÑĢÑĮ
    0.08
    æ·¤
    0.08
    åģıåIJij
    0.08
    دخ
    0.08
    uddy
    0.07
    Activations Density 0.003%

    No Known Activations