© 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. 37887
    Prev
    Next
    INDEX
    Explanations

    copyright and thesis

    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
    éľ²
    -0.11
    reve
    -0.09
    .inc
    -0.09
    åģļèµ·
    -0.09
     tou
    -0.09
    Inc
    -0.09
     cán
    -0.08
    åļ¼
    -0.08
    éĢ¢
    -0.08
    èħĮ
    -0.08
    POSITIVE LOGITS
    èĪĢ
    0.10
    çĽĸ
    0.09
    èݨ
    0.09
    åĿļæĮģä¸įæĩĪ
    0.09
    ÇIJ
    0.09
    ä¸įèĪį
    0.09
    æ±ł
    0.08
    æ´¾
    0.08
    åĬłçĽĸ
    0.08
    åľ¨è¿ĩ渡
    0.08
    Activations Density 0.049%

    No Known Activations