© 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. 39965
    Prev
    Next
    INDEX
    Explanations

    numbers and quantifiers

    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
    趣
    -0.12
    æĥħ人
    -0.10
    æĢ»æĶ¶åħ¥
    -0.10
    çĪ·
    -0.09
    åįģä¸īäºĶ
    -0.09
    éļıæŶ
    -0.09
    èıĬ
    -0.09
    æŁı
    -0.09
    å¹½
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    POSITIVE LOGITS
     remaining
    0.10
    remaining
    0.10
    lef
    0.09
    st
    0.09
    annel
    0.08
    ett
    0.08
    .timedelta
    0.08
     показ
    0.08
    currently
    0.08
    ahir
    0.08
    Activations Density 0.143%

    No Known Activations