© 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. 54418
    Prev
    Next
    INDEX
    Explanations

    career start

    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
    é¾Ļæ³ī
    -0.09
    ien
    -0.09
    çĸĹ
    -0.08
     Gast
    -0.08
    ä»ĭ
    -0.08
    ç£ĭåķĨ
    -0.08
    躲
    -0.08
    åĥ»
    -0.08
    壤
    -0.08
    _DOT
    -0.08
    POSITIVE LOGITS
    æĪIJåIJį
    0.11
    åħ¥éŨ
    0.10
     ê¶Į
    0.10
    lingen
    0.10
    éĤ£æ®µ
    0.10
    å¿Į
    0.09
    _VISIBLE
    0.09
    ä¸įèĥ½åĨį
    0.09
     Shel
    0.09
    çļĦå°ı
    0.09
    Activations Density 0.095%

    No Known Activations