© 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. 36005
    Prev
    Next
    INDEX
    Explanations

    guide system

    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
    éĺŁåijĺ
    -0.09
    ptrdiff
    -0.08
    ICY
    -0.08
    éĺŁåijĺ们
    -0.08
    æ»ŀåIJİ
    -0.08
    æ®Ĭ
    -0.08
    大äºĭ
    -0.08
    çºłéĶĻ
    -0.08
    åıĤè§Ĥ
    -0.08
    åĽ¢åijĺ
    -0.08
    POSITIVE LOGITS
    æķĻç¨ĭ
    0.13
    æĮĩåįĹ
    0.13
    æĶ»çķ¥
    0.13
    书ç±į
    0.12
    ä¸Ģæľ¬
    0.12
    èĤ²åĦ¿
    0.12
    æķĻ导
    0.11
    讲座
    0.11
    æĬĢæ³ķ
    0.11
     guides
    0.11
    Activations Density 0.309%

    No Known Activations