© 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. 52682
    Prev
    Next
    INDEX
    Explanations

    IRC bot, php, code comments

    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
    çĭ¬
    -0.09
    Mailer
    -0.09
    éĴ®
    -0.08
    åĩºåı°äºĨ
    -0.08
    amb
    -0.08
    åĩºåı°
    -0.08
    _CRE
    -0.08
    æĴ¥
    -0.08
    åĪ¶éĢł
    -0.08
    azz
    -0.08
    POSITIVE LOGITS
    éķ¿æĺ¥
    0.11
    åıŁ
    0.11
    主æĮģ人
    0.10
    饮水
    0.10
    åĬłåħ¥
    0.10
    å¾Īæ·±
    0.10
    ä¸ĢåĪĢ
    0.10
    æĪĴ
    0.09
    åIJ¬åIJ¬
    0.09
    æĪļ
    0.09
    Activations Density 0.060%

    No Known Activations