© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52919
    Prev
    Next
    INDEX
    Explanations

    discovery and development

    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
    积
    -0.09
    èijµ
    -0.09
    hausen
    -0.09
     Balt
    -0.08
    ç£
    -0.08
    è°ĭæ±Ĥ
    -0.08
    ika
    -0.08
    สะสม
    -0.08
    اÙĦØ©
    -0.08
    èį¡
    -0.08
    POSITIVE LOGITS
    åıijçİ°
    0.26
    åıijçİ°äºĨ
    0.24
     discovery
    0.23
    çĻ¼çı¾
    0.21
     discover
    0.20
     discovered
    0.19
     discoveries
    0.18
    discover
    0.18
     Discover
    0.17
    æīįåıijçİ°
    0.17
    Activations Density 0.394%

    No Known Activations