© 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. 4649
    Prev
    Next
    INDEX
    Explanations

    filmmaker

    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
    adem
    -0.09
    å·§
    -0.08
    æĭ¾
    -0.08
    æĭ£
    -0.08
    ç©¿è¶Ĭ
    -0.08
    ulg
    -0.08
    dÃŃ
    -0.08
    秦çļĩ
    -0.08
    oug
    -0.08
    说ä»Ģä¹Ī
    -0.08
    POSITIVE LOGITS
    ographics
    0.09
    è¿Ľä¿®
    0.09
    æŁ±
    0.09
    round
    0.09
    åĵģå°Ŀ
    0.09
     Tate
    0.09
    å¤ļåľ°
    0.08
     camel
    0.08
    juan
    0.08
    身åIJİ
    0.08
    Activations Density 0.043%

    No Known Activations