© 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. 36422
    Prev
    Next
    INDEX
    Explanations

    cup or tsp

    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
    éĿ
    -0.10
    çŀ¥
    -0.10
    soup
    -0.09
    зоÑĢ
    -0.09
    èijŃ
    -0.09
    ä½ĵè´¨
    -0.09
     clen
    -0.09
    ARSE
    -0.09
    çªĹå¤ĸ
    -0.09
    æĵį
    -0.09
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.09
     pro
    0.09
     freshly
    0.08
    èį£
    0.08
     اÙĦÙĪاØŃد
    0.08
     tasar
    0.08
    ful
    0.08
    å·¦åı³
    0.08
    å¼¼
    0.08
    ëŁī
    0.08
    Activations Density 0.003%

    No Known Activations