© 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. 36365
    Prev
    Next
    INDEX
    Explanations

    benefit and fundraising events

    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
    éĢ¢
    -0.09
    åĬĪ
    -0.09
     reb
    -0.09
     Reb
    -0.08
    .experimental
    -0.08
    æ¾Ī
    -0.08
    mojom
    -0.08
    èĤī
    -0.08
    æ¿ĢåĬ±
    -0.08
     Sevilla
    -0.07
    POSITIVE LOGITS
    åħ¬çĽĬ
    0.12
    åıªæĺ¯ä¸ºäºĨ
    0.11
    éĿ¢åŃIJ
    0.10
    å°±æĺ¯ä¸ºäºĨ
    0.10
    ä¸¤å¼ł
    0.09
    åıĭæĥħ
    0.09
    衲
    0.09
    æģ¤
    0.09
    鸳
    0.09
     Gilbert
    0.09
    Activations Density 0.183%

    No Known Activations