© 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. 49883
    Prev
    Next
    INDEX
    Explanations

    Best followed by award categories

    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
    çĺ¾
    -0.09
    åģļèµ·
    -0.08
    å¿Ĺ强
    -0.08
    æĪIJ为äºĨ
    -0.08
    欹
    -0.08
     hol
    -0.08
    ãģĹãģĭãģªãģĦ
    -0.08
    å¤ļå¤ļ
    -0.08
    è¾¾ä¸įåĪ°
    -0.08
    æĢ»æī¿åĮħ
    -0.08
    POSITIVE LOGITS
    _UNS
    0.10
    omething
    0.10
    ä½ķåĨµ
    0.10
     ÑģобÑģÑĤвенно
    0.09
    	TokenName
    0.09
    æĸ¥
    0.09
    cue
    0.09
    inkle
    0.09
    uada
    0.09
    ordes
    0.08
    Activations Density 0.018%

    No Known Activations