© 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. 51963
    Prev
    Next
    INDEX
    Explanations

    getting ready for

    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
    emes
    -0.10
    inoa
    -0.09
    èģĶ缣
    -0.08
    olem
    -0.08
    纵
    -0.08
    æŁIJç§įç¨ĭ度
    -0.08
    irit
    -0.08
    éĻ¤éĿŀ
    -0.08
    Kind
    -0.08
    lessly
    -0.08
    POSITIVE LOGITS
    wards
    0.09
    uffed
    0.08
    bih
    0.08
    è¿İæİ¥
    0.08
    çļĦè¿ĩç¨ĭä¸Ń
    0.08
    -sama
    0.08
    æ±°
    0.08
    æĭ©
    0.08
    æ¯Ľ
    0.08
    åIJĥäºı
    0.08
    Activations Density 0.006%

    No Known Activations