© 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. 10480
    Prev
    Next
    INDEX
    Explanations

    or

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.10
    æĪĸåħ¶ä»ĸ
    -0.10
    æĪijè¿ĺ
    -0.10
    åħ¶ä»ĸ
    -0.10
    embro
    -0.10
    letal
    -0.10
    mA
    -0.09
    ÙĦت
    -0.09
    moth
    -0.09
    身为
    -0.09
    POSITIVE LOGITS
    leans
    0.08
    éĻĽä¸ĭ
    0.08
    lip
    0.07
    iant
    0.07
    ied
    0.07
    ä¸Ģ个å¤ļæľĪ
    0.07
    ogen
    0.07
    ering
    0.07
    cade
    0.07
    åĭº
    0.07
    Activations Density 0.170%

    No Known Activations