© 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. 7642
    Prev
    Next
    INDEX
    Explanations

    special challenges or implications

    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
     Gad
    -0.09
    lush
    -0.09
    èĢ¿
    -0.09
    åįī
    -0.09
    AO
    -0.08
    举ä¾ĭ
    -0.08
    PIP
    -0.08
    -setup
    -0.08
     toItem
    -0.08
    åĽŀåij³
    -0.08
    POSITIVE LOGITS
    çļĦéĹ®é¢ĺ
    0.12
    带æĿ¥
    0.11
    æĮijæĪĺ
    0.10
    带æĿ¥æĽ´å¤ļ
    0.10
    åĮħ袱
    0.10
     challenges
    0.10
    带çĿĢ
    0.10
    é£İæĥħ
    0.10
    帶èijĹ
    0.10
    çĸijéĹ®
    0.09
    Activations Density 0.071%

    No Known Activations