© 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. 3647
    Prev
    Next
    INDEX
    Explanations

    which/and/after/but/from clauses

    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
    ä¸įçķĻ
    -0.10
    污
    -0.08
    éĤ£å°±æĺ¯
    -0.08
    AREN
    -0.08
    æľīç§į
    -0.08
    åĽłåħ¶
    -0.08
    .MoveNext
    -0.08
    èĨº
    -0.07
    ç¸
    -0.07
    loh
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸ī个
    0.13
    è¿Ļ两个
    0.10
    è¿Ļåĩłä¸ª
    0.09
    cestor
    0.09
    ä¸īä½įä¸Ģä½ĵ
    0.09
    icide
    0.09
    odash
    0.08
    è¿Ļ两
    0.08
    аÑĤелÑĮ
    0.08
     odom
    0.08
    Activations Density 0.446%

    No Known Activations