© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    subscriber to another

    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
    chers
    -0.12
    ungi
    -0.11
    jec
    -0.10
    nik
    -0.09
    ledon
    -0.09
    à¹Ĥà¸Ľà¸£à¹ģ
    -0.09
     Bett
    -0.09
    ApiController
    -0.09
    åħĪ导
    -0.09
    quee
    -0.09
    POSITIVE LOGITS
    æĪĸå¤ļæĪĸå°ij
    0.10
    å¾ĢåIJİ
    0.10
    诸å¦Ĥ
    0.10
    è¦ĨçĽĸéĿ¢
    0.10
    æĶ¹éĿ©åĪĽæĸ°
    0.09
    ä¼ļè§īå¾Ĺ
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    çIJ
    0.09
    ä¸į管æĺ¯
    0.09
    ä¸į论
    0.09
    Activations Density 0.001%

    No Known Activations