© 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. 32996
    Prev
    Next
    INDEX
    Explanations

    bedroom, playing, toys

    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
    åĻİ
    -0.09
    涣
    -0.08
    ç¬ij声
    -0.08
    çīµ
    -0.08
     гол
    -0.08
    æĹģ
    -0.08
    çĥĽ
    -0.08
    代价
    -0.08
    åį¿
    -0.08
    满
    -0.08
    POSITIVE LOGITS
    åį§å®¤
    0.11
    æĬĬèĩªå·±
    0.10
    çŃ¹éĽĨ
    0.10
    æĿĤçī©
    0.10
    -bedroom
    0.09
    çľ¼çľĭ
    0.09
    ç¡IJ
    0.09
     книги
    0.09
    æĭ¦æĪª
    0.09
    常çĶ¨
    0.09
    Activations Density 0.064%

    No Known Activations