© 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. 56487
    Prev
    Next
    INDEX
    Explanations

    start or begin

    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
     Teh
    -0.09
    Ñģкоп
    -0.09
    æĬĵç´§
    -0.09
    æ¹ĸåĮº
    -0.09
    ntax
    -0.08
    ngen
    -0.08
    æ¹ĸ
    -0.08
    наÑĤ
    -0.08
    auty
    -0.08
     Disorder
    -0.08
    POSITIVE LOGITS
    å§ĭäºİ
    0.15
    æĸ°å¾ģç¨ĭ
    0.12
    æĸ°çļĦä¸Ģ
    0.11
    èµ·çĤ¹
    0.11
    èµ·æŃ¥
    0.11
    çĿĢæīĭ
    0.11
    :start
    0.10
    pers
    0.10
     started
    0.10
     starts
    0.10
    Activations Density 0.257%

    No Known Activations