© 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. 9983
    Prev
    Next
    INDEX
    Explanations

    Arboretum, magazine, registry

    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
    ÅIJ
    -0.10
    å¥Ķ
    -0.10
    å±IJ
    -0.09
    ä¸įå¿į
    -0.09
    chg
    -0.09
    jes
    -0.09
    ÑģÑĤанов
    -0.09
    unken
    -0.09
     اÙĦسÙħ
    -0.09
    æĥħ人
    -0.09
    POSITIVE LOGITS
    ä¸ĢæľŁ
    0.10
    è½½ä½ĵ
    0.09
    渲
    0.09
    ä¸Ģç¬Ķ
    0.08
    çĶŁåij½åĬĽ
    0.08
    æīįèĥ½å¤Ł
    0.08
    å¾ĩ
    0.08
    è¼ī
    0.08
    æºŁ
    0.08
    大è¡Ĺ
    0.08
    Activations Density 0.073%

    No Known Activations