© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31211
    Prev
    Next
    INDEX
    Explanations

    java class or applet

    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
    å³°
    -0.09
    gone
    -0.09
    DEST
    -0.09
    æѧ
    -0.09
     FAG
    -0.09
    çľĭä»ĸ
    -0.08
    æī©å»º
    -0.08
    åĬĪ
    -0.08
    atl
    -0.08
     rub
    -0.08
    POSITIVE LOGITS
    ä¿Ŀä¿®
    0.10
    ehr
    0.09
    Specifier
    0.09
     ÐijолÑĮ
    0.09
    æ§Į
    0.09
     RemoteException
    0.09
    ä¸ĩ象
    0.09
    loy
    0.09
    èĢĥ
    0.09
    æ»ŀåIJİ
    0.08
    Activations Density 0.206%

    No Known Activations