© 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. 48406
    Prev
    Next
    INDEX
    Explanations

    medical and law schools

    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
    è¿ŀäºij
    -0.08
     Irish
    -0.08
    atic
    -0.08
    çݰ代åĮĸ
    -0.08
    æīįçŁ¥éģĵ
    -0.08
    åij¤
    -0.08
    ÙĪÙĬ
    -0.08
    /dat
    -0.08
    çĭ¬è§Ĵ
    -0.08
    ç»ĵæŀĦè°ĥæķ´
    -0.08
    POSITIVE LOGITS
    nyder
    0.10
    ibrary
    0.09
    室
    0.09
     serge
    0.09
    низ
    0.09
    ode
    0.08
    çķĮçļĦ
    0.08
    æĹ¥æŃ£å¼ı
    0.08
    严
    0.08
    ervatives
    0.08
    Activations Density 0.006%

    No Known Activations