© 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. 30977
    Prev
    Next
    INDEX
    Explanations

    software code equipment

    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
    ä¸ĢèĦļ
    -0.10
    们çļĦ
    -0.10
    们
    -0.09
    俾
    -0.08
    parts
    -0.08
    conti
    -0.08
    itur
    -0.08
    使åħ¶
    -0.08
    èĢģçĪ·
    -0.08
    æİĪ
    -0.08
    POSITIVE LOGITS
    amt
    0.10
    inux
    0.10
    çĶŁæĢģç³»ç»Ł
    0.09
     piece
    0.09
    -initialized
    0.09
    æĥ³èµ·æĿ¥
    0.09
    æīĢè°ĵ
    0.08
    etz
    0.08
    ä»Ģä¹Īåij¢
    0.08
    åĪ¶åĵģ
    0.08
    Activations Density 0.522%

    No Known Activations