© 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. 23715
    Prev
    Next
    INDEX
    Explanations

    old blog posts

    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
    åħ¶æīĢ
    -0.10
    æĺ¯æĪijåĽ½
    -0.10
    amar
    -0.09
    饿
    -0.09
    afs
    -0.09
    裤åŃIJ
    -0.09
    ORN
    -0.09
     counterpart
    -0.09
    éĥ¨éĥ¨éķ¿
    -0.09
    èħ¿éĥ¨
    -0.09
    POSITIVE LOGITS
    æIJŀå®ļ
    0.09
    äºĭä¸ļåıijå±ķ
    0.09
    å·²æĺ¯
    0.09
     Chiefs
    0.08
    è¿Ļè¾¹
    0.08
    èĤĮ
    0.08
    ãĥijãĥ¼
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    town
    0.08
    å¿ĸ
    0.08
    Activations Density 0.141%

    No Known Activations