© 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. 38563
    Prev
    Next
    INDEX
    Explanations

    inverter, Desert, construction, lymphocytes, Friday

    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
    ä¼łç»ŁçļĦ
    -0.09
    ainen
    -0.09
    å¡«è¡¥
    -0.09
    decoded
    -0.09
    uml
    -0.09
    ä¼łæī¿
    -0.09
    htub
    -0.09
    éļIJ约
    -0.09
    åĤ¬
    -0.08
    assis
    -0.08
    POSITIVE LOGITS
    åħīä¼ı
    0.12
    çħ§äº®
    0.10
     solar
    0.10
    太éĺ³èĥ½
    0.10
    åľ°åĿĹ
    0.10
    è¿IJèIJ¥åķĨ
    0.10
    çĶµç«Ļ
    0.09
    åħīä¼ıåıijçĶµ
    0.09
    è¿IJç»´
    0.09
    ä¸Ģè¾ĪåŃIJ
    0.09
    Activations Density 0.058%

    No Known Activations