© 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. 19925
    Prev
    Next
    INDEX
    Explanations

    process of

    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
    紧迫
    -0.09
    æ¶ī
    -0.09
    åıªæĺ¯ä¸Ģ个
    -0.09
    åij¼åĶ¤
    -0.09
    宥
    -0.09
    çķĻåŃĺ
    -0.09
    èĮħ
    -0.09
    ç½Ł
    -0.08
    _CURSOR
    -0.08
    çĬį
    -0.08
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭ
    0.11
     process
    0.10
    è¿ĩç¨ĭ
    0.09
    dsl
    0.09
    æĻ¯å¾·
    0.09
    对æİ¥
    0.09
    æĭ¿
    0.08
    éģİç¨ĭ
    0.08
    odem
    0.08
    (collection
    0.08
    Activations Density 0.160%

    No Known Activations