© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51565
    Prev
    Next
    INDEX
    Explanations

    numbers and sports jerseys

    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
    çģŃ
    -0.09
    骡
    -0.09
    审æī¹
    -0.09
    类似çļĦ
    -0.09
    åįģ个
    -0.09
    æ»ħ
    -0.08
    æį»
    -0.08
    驱
    -0.08
    é³Į
    -0.08
    管çIJĨéĥ¨éŨ
    -0.08
    POSITIVE LOGITS
    åı·çłģ
    0.13
    ç¼ĸåı·
    0.11
    åı·
    0.11
     номеÑĢ
    0.11
     numbered
    0.09
    æ±°
    0.09
    -number
    0.09
    ÑģÑĤа
    0.08
    åħ¸
    0.08
    à¹Ģลà¸Ĥ
    0.08
    Activations Density 0.033%

    No Known Activations