© 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. 57018
    Prev
    Next
    INDEX
    Explanations

    payment and cost

    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
    Leave
    -0.09
     calculus
    -0.08
     leave
    -0.08
    åı¯ä¾Ľ
    -0.08
    cen
    -0.08
    RAW
    -0.08
    orsk
    -0.08
    æѧ
    -0.08
    积
    -0.08
    éĶĢåĶ®æĶ¶åħ¥
    -0.08
    POSITIVE LOGITS
    ä»ĺåĩº
    0.14
    ä»ĺ
    0.12
    ä¹°çļĦ
    0.11
     Rope
    0.11
    代价
    0.10
    æĶ¯ä»ĺ
    0.10
    è´Łæĭħ
    0.10
    ä¹°åįķ
    0.10
    ä¹°åĪ°
    0.10
     barg
    0.10
    Activations Density 0.188%

    No Known Activations