© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36985
    Prev
    Next
    INDEX
    Explanations

    container parts or types

    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
     iso
    -0.10
    Iso
    -0.10
    åĨį说
    -0.09
    iso
    -0.09
     Iso
    -0.09
    è©Ī
    -0.09
    å¦ĤæĦı
    -0.09
    缴è¾ĸ
    -0.08
    èĤīä½ĵ
    -0.08
    uur
    -0.08
    POSITIVE LOGITS
    çĵ¶
    0.16
    çĵ¶åŃIJ
    0.13
     bottle
    0.13
    åĽŀæĶ¶
    0.11
    аÑĢа
    0.11
    壳
    0.10
    çªĹ
    0.10
     bottles
    0.10
    æĶĴ
    0.10
    åĵ¨
    0.09
    Activations Density 0.080%

    No Known Activations