© 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. 28021
    Prev
    Next
    INDEX
    Explanations

    born and raised

    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
    ishi
    -0.09
    ATO
    -0.09
    ä¸ĢæŶ
    -0.09
    éij«
    -0.09
    æ¯ħåĬĽ
    -0.08
    åĨĴ
    -0.08
    åĢŁæѤ
    -0.08
    leaf
    -0.08
    èĤª
    -0.08
    éļ
    -0.08
    POSITIVE LOGITS
    åĨľå®¶
    0.11
    çļĦéĩį大
    0.09
    侯
    0.09
     impress
    0.09
    ÑĥлÑĮ
    0.09
    ãģıãĤĵ
    0.09
    æ¯ĹéĤ»
    0.09
     gran
    0.09
    åĪ«è¯´
    0.08
    è¿Ļä¹Īåģļ
    0.08
    Activations Density 0.009%

    No Known Activations