© 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. 61815
    Prev
    Next
    INDEX
    Explanations

    best prices/rates

    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
    .tab
    -0.10
    æĬ¢
    -0.09
    /tab
    -0.09
    çĭ¼
    -0.09
    mun
    -0.09
    ij
    -0.08
     Daniels
    -0.08
    裱
    -0.08
    aan
    -0.08
     изделиÑı
    -0.08
    POSITIVE LOGITS
    ç»ĪçĶŁ
    0.09
    ç»Ī身
    0.09
    èĢģåħ¬
    0.09
     Most
    0.08
    æѦè£ħ
    0.08
    亲èĩª
    0.08
    书éĿ¢
    0.07
    apos
    0.07
    å¹ħ度
    0.07
    娱
    0.07
    Activations Density 0.002%

    No Known Activations