© 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. 1530
    Prev
    Next
    INDEX
    Explanations

    tent, shelter

    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
    活泼
    -0.09
    velle
    -0.09
    TH
    -0.09
    åIJİå¤ĩ
    -0.08
    é¢Ħæ¡Ī
    -0.08
    åĿıäºĭ
    -0.08
    å¹³æŶ
    -0.08
    reserve
    -0.08
    æ¢Ĺ
    -0.08
    åıĺæĢģ
    -0.08
    POSITIVE LOGITS
    å¸IJ篷
    0.18
     tents
    0.13
    tent
    0.13
    èĪ±
    0.13
    篷
    0.12
    éĥ¨èIJ½
    0.12
     tent
    0.11
    纺ç»ĩ
    0.11
    æIJŃ建
    0.10
    å¹ķ
    0.10
    Activations Density 0.073%

    No Known Activations