© 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. 9522
    Prev
    Next
    INDEX
    Explanations

    overland

    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
    ENTA
    -0.10
    annon
    -0.09
    次
    -0.09
    ино
    -0.09
    jas
    -0.09
    reo
    -0.09
    åĮł
    -0.09
    秤
    -0.09
    ä¸ĬéŨ
    -0.09
    æµ·è¾¹
    -0.08
    POSITIVE LOGITS
    most
    0.09
    edly
    0.09
    ç»Ļ人ä¸Ģç§į
    0.09
    绣
    0.09
    arching
    0.08
    wed
    0.08
    åı¬éĽĨ
    0.08
    æĸ°è¥¿åħ°
    0.08
    izer
    0.08
    th
    0.08
    Activations Density 0.006%

    No Known Activations