© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51192
    Prev
    Next
    INDEX
    Explanations

    processing, approval, review, evaluation

    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
    ä¹Łä¸įæĥ³
    -0.09
    ishi
    -0.08
    owe
    -0.08
    åģ¥
    -0.08
    åĺİ
    -0.08
    ivation
    -0.08
    ç©·
    -0.08
    OW
    -0.08
    éļį
    -0.08
    ä¿¡èµĸ
    -0.08
    POSITIVE LOGITS
    å·¾
    0.10
     Tear
    0.10
    éļħ
    0.10
    olah
    0.09
    éĤ£åĦ¿
    0.09
    éĤ£éĩĮ
    0.09
    åij½
    0.09
    è¾ĩ
    0.09
    è´¨åľ°
    0.09
    åIJİåĨį
    0.09
    Activations Density 0.052%

    No Known Activations