© 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. 49814
    Prev
    Next
    INDEX
    Explanations

    upon followed by action or state

    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
    éļ¾
    -0.09
    å²Į
    -0.09
    æīĵå¾Ĺ
    -0.09
    åĭĩäºİ
    -0.09
     serialVersionUID
    -0.08
    åĽ«
    -0.08
    çĮ¶
    -0.08
     nạn
    -0.08
    Nie
    -0.08
    æ®ĭçķĻ
    -0.08
    POSITIVE LOGITS
    å¾ĹçŁ¥
    0.11
     upon
    0.11
    åĪ°æĿ¥
    0.11
    Upon
    0.11
    éķ¿å¤§
    0.11
     Upon
    0.11
    å½ĴæĿ¥
    0.10
    åħ¥å¸Ĥ
    0.10
     receipt
    0.10
    è¸ıåħ¥
    0.10
    Activations Density 0.080%

    No Known Activations