© 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. 53501
    Prev
    Next
    INDEX
    Explanations

    plants and cultivation

    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
    èĬ±èįī
    -0.14
    èĬ½
    -0.10
    ç«Ļ
    -0.10
    æľīçĽĬ
    -0.09
    å½ĵåľº
    -0.09
    åĨľä½ľçī©
    -0.09
    åĪĨ辨
    -0.09
    秧
    -0.09
    èĬ³
    -0.08
    车ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    åºŁ
    0.09
    éĹ²
    0.08
    .processor
    0.08
     scraps
    0.08
    ouis
    0.08
    æ´Ĺ
    0.08
    å¤ļä¸ªåĽ½å®¶
    0.08
    Liked
    0.08
     pivot
    0.08
    Sizer
    0.08
    Activations Density 0.062%

    No Known Activations