© 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. 22412
    Prev
    Next
    INDEX
    Explanations

    monthly payments

    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
    æīĭå¥Ĺ
    -0.10
    æĪij家
    -0.09
    outu
    -0.09
    =\"#
    -0.09
    éħį
    -0.09
    èįī
    -0.09
    çī¹åĪ«å£°æĺİ
    -0.09
    水墨
    -0.09
    _switch
    -0.08
    æijĦ
    -0.08
    POSITIVE LOGITS
    åĪĨæľŁ
    0.11
    屿
    0.10
    æ¶ĪåĮĸ
    0.10
    æĭ®
    0.09
    ä»ĺ款
    0.09
    ILT
    0.09
    è´«åĽ°äººåı£
    0.09
    åŃ½
    0.09
    åħ¬åı¸ç«łç¨ĭ
    0.08
     installment
    0.08
    Activations Density 0.044%

    No Known Activations