© 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. 55877
    Prev
    Next
    INDEX
    Explanations

    youth substance use prevention

    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
    ä¿®çIJĨ
    -0.10
    åıij
    -0.10
    æī§è¡ĮåĬĽ
    -0.09
    ÙħصÙĦØŃØ©
    -0.09
    Ø£ÙĪضاع
    -0.09
    æ§Ľ
    -0.09
    çijķçĸµ
    -0.09
    legg
    -0.09
    ä¸ĭåıij
    -0.08
    éļ¾
    -0.08
    POSITIVE LOGITS
    åĬĿ
    0.10
    åIJİæŀľ
    0.09
    åĪ¶æŃ¢
    0.09
    ä¸Ńå¿ĥåŁİåĮº
    0.08
    éĻ¡
    0.08
    说æľį
    0.08
    mars
    0.08
    éĢŀ
    0.08
     campuses
    0.08
    assage
    0.08
    Activations Density 0.087%

    No Known Activations