© 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. 49213
    Prev
    Next
    INDEX
    Explanations

    incorporate or integrate into

    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
    æ¯ķç«Łæĺ¯
    -0.09
    积
    -0.09
    nis
    -0.09
    ãģĵãģ¨ãģ§
    -0.09
    AttributeValue
    -0.09
    rei
    -0.08
    çĶ«
    -0.08
    æ¼Ĩ
    -0.08
    æĺĮ
    -0.08
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
    POSITIVE LOGITS
     into
    0.16
    Into
    0.15
     vÃło
    0.13
    into
    0.12
     Into
    0.12
     INTO
    0.12
    èŀįåħ¥
    0.12
    _into
    0.11
    è¿ĽæĿ¥
    0.11
    çļĦæĢĿæĥ³
    0.11
    Activations Density 0.042%

    No Known Activations