© 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. 63436
    Prev
    Next
    INDEX
    Explanations

    for or as followed by a word

    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
    istr
    -0.09
    åı¦æľī
    -0.09
    anth
    -0.09
    æ·¡
    -0.08
    .lookup
    -0.08
    åĪ°æĿ¥
    -0.08
    .gf
    -0.08
    ä¿Ŀä¿®
    -0.08
    é¢ł
    -0.08
    å§ĭ建
    -0.08
    POSITIVE LOGITS
    驱
    0.10
     каÑĩеÑģÑĤве
    0.09
    yla
    0.09
    éħį
    0.09
    åĩĨ
    0.08
    æĻļé¤IJ
    0.08
    è´£ç¼ĸ
    0.08
     пÑĢид
    0.08
    åĽŀçŃĶ
    0.08
    主
    0.08
    Activations Density 0.181%

    No Known Activations