© 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. 36846
    Prev
    Next
    INDEX
    Explanations

    cycl Gonzalez cyclodextrin

    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
    ably
    -0.12
    ities
    -0.11
     sÃłng
    -0.11
     rÃłng
    -0.10
    ances
    -0.09
    ents
    -0.09
    URN
    -0.09
    że
    -0.09
    æīĭæİĮ
    -0.08
    ¡
    -0.08
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.10
    ãģĹãģ¾ãģĦ
    0.10
    åī¯å±Ģéķ¿
    0.09
    åĽłä¸ºåľ¨
    0.09
    naire
    0.09
    idal
    0.09
    ÑģÑı
    0.09
    éļ¾åħį
    0.09
    ello
    0.08
    èĻ±
    0.08
    Activations Density 0.105%

    No Known Activations