© 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. 31316
    Prev
    Next
    INDEX
    Explanations

    phrases ending with out

    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
    éģĵ士
    -0.10
    èŀĪ
    -0.09
    è¡ĮåĬ¨è®¡åĪĴ
    -0.09
    çĸ«èĭĹ
    -0.09
    ITE
    -0.09
    æ¹¾
    -0.09
    ä¸įèµ·
    -0.09
    anker
    -0.08
    éŃĤ
    -0.08
    è´¤
    -0.08
    POSITIVE LOGITS
    eph
    0.09
    éĴĿ
    0.09
    æŁľ
    0.08
    rapped
    0.08
    åıijæİĺ
    0.08
    hé
    0.08
    pars
    0.08
    æľīæĿ¡ä»¶çļĦ
    0.08
    å¤§èµĽ
    0.08
    Ton
    0.07
    Activations Density 0.021%

    No Known Activations