© 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. 9590
    Prev
    Next
    INDEX
    Explanations

    assign then using

    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
    olib
    -0.09
    ä»»ä½ķä¸Ģ个
    -0.09
    ä»»ä½ķ人
    -0.09
     Skinner
    -0.09
     вообÑīе
    -0.08
    çŃī人
    -0.08
    orsi
    -0.08
    èĬĴ
    -0.08
    ä»»ä½ķ
    -0.08
    æĹ·
    -0.08
    POSITIVE LOGITS
    对该
    0.11
    تÙĬÙĨ
    0.09
    ìī¬
    0.09
    azzi
    0.09
     capture
    0.08
    åī
    0.08
    åĹĶ
    0.08
    åij¼åĴĮ
    0.08
    éĢģåİ»
    0.08
    æıŃéľ²
    0.08
    Activations Density 1.646%

    No Known Activations