© 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. 33663
    Prev
    Next
    INDEX
    Explanations

    SAP and related company/software names

    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
    naire
    -0.10
    edList
    -0.10
    ·
    -0.09
    趾
    -0.09
    ä¸įä½ı
    -0.09
    edio
    -0.09
    isko
    -0.09
    liness
    -0.08
    以åħį
    -0.08
    æīİå®ŀæİ¨è¿Ľ
    -0.08
    POSITIVE LOGITS
    0.11
    TEE
    0.10
    pery
    0.09
    åįĪ
    0.09
    FRAME
    0.09
    hte
    0.09
    ÑĨе
    0.09
    frame
    0.09
    ../
    0.09
    UME
    0.08
    Activations Density 0.087%

    No Known Activations