© 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. 1364
    Prev
    Next
    INDEX
    Explanations

    Melvin, melanoma, melon

    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
    sWith
    -0.13
    stellung
    -0.09
    ¬
    -0.08
    ãģĦãĤĭ
    -0.08
    swith
    -0.08
    sw
    -0.08
    elijk
    -0.08
    eer
    -0.08
    æķĸ
    -0.08
    pers
    -0.08
    POSITIVE LOGITS
    bourne
    0.14
    otype
    0.10
    åIJ®
    0.10
    漪
    0.10
     tide
    0.09
    opsy
    0.09
    çħ
    0.09
    åĨľä¸ļ大åѦ
    0.09
    èĥĨ
    0.09
    å´¦
    0.09
    Activations Density 0.032%

    No Known Activations