© 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. 26543
    Prev
    Next
    INDEX
    Explanations

    presentation of, take a, to a

    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
    æĪ¶
    -0.09
    å±ģ
    -0.09
     Brett
    -0.09
    alle
    -0.09
    ä»Ģä¹Īéĥ½
    -0.08
    åŃľ
    -0.08
    åŁİå¢Ļ
    -0.08
    çī¹æ®ĬçļĦ
    -0.08
     ÑģÑĤанд
    -0.08
    çĭ¬æľīçļĦ
    -0.08
    POSITIVE LOGITS
    让å®ĥ
    0.10
    åıī
    0.09
    istically
    0.09
    çĤ¹äº®
    0.08
    enga
    0.08
    æį§
    0.08
    lust
    0.08
    æľīåĩłä¸ª
    0.08
    TextNode
    0.08
    istical
    0.08
    Activations Density 0.182%

    No Known Activations