© 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. 36239
    Prev
    Next
    INDEX
    Explanations

    world | global

    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
    sei
    -0.10
    ä¸Ģæī¹
    -0.10
    zzle
    -0.09
    iad
    -0.09
    .MinValue
    -0.08
    _boot
    -0.08
    INDER
    -0.08
    finder
    -0.08
     Finder
    -0.08
     п
    -0.08
    POSITIVE LOGITS
    åĨį次
    0.10
    éªħ
    0.09
    izr
    0.09
    大å®ĹåķĨåĵģ
    0.08
    缨
    0.08
    _OC
    0.08
    æĸ°å½¢åĬ¿
    0.08
    SetName
    0.08
    é»Ħéĩij
    0.08
    幸ç¦ıæĦŁ
    0.08
    Activations Density 0.054%

    No Known Activations