© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21602
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions

    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
    æĹĦ
    -0.09
    æīĵåį¡
    -0.09
    ieur
    -0.09
    .Persistence
    -0.08
    iew
    -0.08
    åĽłä¸ºæĪij们
    -0.08
    æģ°å¥½
    -0.08
    è¿Ļæł·ä¸Ģ
    -0.08
    åĮºå§Ķ
    -0.08
    è§Ĵ度æĿ¥çľĭ
    -0.08
    POSITIVE LOGITS
    stakes
    0.09
    认为
    0.09
    åıĹ访èĢħ
    0.09
    ammers
    0.09
    æĬ¥åijĬæĺ¾ç¤º
    0.09
     опÑĭÑĤ
    0.09
    表示
    0.08
    çľ¼è¢ĭ
    0.08
     enumer
    0.08
    RLF
    0.08
    Activations Density 0.083%

    No Known Activations