© 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. 39938
    Prev
    Next
    INDEX
    Explanations

    numbers followed by groups of people

    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
    IGNAL
    -0.10
    اء
    -0.09
    ç¨
    -0.09
    æ¯ĶåĪ©
    -0.09
    éĿ¡
    -0.09
    ammen
    -0.09
    asser
    -0.09
    大夫
    -0.09
    à§İ
    -0.09
    大éĺŁ
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³
    0.10
    ilder
    0.10
    å°±åĮ»
    0.09
    ä¸ĭéĿ¢å°±
    0.09
    éĢĨ
    0.09
    vern
    0.09
    åİ»è¿ĩ
    0.09
    顽
    0.08
    iard
    0.08
    ä¹ĥèĩ³
    0.08
    Activations Density 0.074%

    No Known Activations