© 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. 48743
    Prev
    Next
    INDEX
    Explanations

    competing for

    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
    å§Ķç»Ħç»ĩ
    -0.09
    æıĨ
    -0.09
    æĪĸå¤ļæĪĸå°ij
    -0.09
    è·Łè¿Ľ
    -0.09
    ä»ĸèĩªå·±
    -0.08
    Danny
    -0.08
    شا
    -0.08
    LEGAL
    -0.08
    atra
    -0.08
    SplitOptions
    -0.08
    POSITIVE LOGITS
    çĶ¨çĶµ
    0.09
    åĮĻ
    0.09
    åĴĮæĬĢæľ¯
    0.09
    天é¹ħ
    0.09
    æĮª
    0.09
    ä¸ĭ称
    0.09
    è¿ħçĮĽ
    0.08
    é«ĺéĢŁåıijå±ķ
    0.08
    çİĭèĢħ
    0.08
    éĥ½è§īå¾Ĺ
    0.08
    Activations Density 0.006%

    No Known Activations