© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21804
    Prev
    Next
    INDEX
    Explanations

    ingredients or food preparation

    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
    æĶ¶åĪ°äºĨ
    -0.11
    ä¸Ģéĺµ
    -0.09
    æģĭ人
    -0.09
    lk
    -0.09
    èĩ´å¯Į
    -0.09
    LocalizedString
    -0.09
    ¬ģ
    -0.09
    çĶŁåij½åĬĽ
    -0.09
    å°±åĥıæĺ¯
    -0.09
    ä½ıéĻ¢
    -0.09
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģ个
    0.09
    unks
    0.09
    æŃ¤é¡¹
    0.08
     assorted
    0.08
    åĪĥ
    0.08
     ready
    0.07
    è¡Į使
    0.07
    çı¥
    0.07
    iefs
    0.07
    chooser
    0.07
    Activations Density 0.025%

    No Known Activations