© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51497
    Prev
    Next
    INDEX
    Explanations

    this followed by noun

    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
     дÑĢÑĥг
    -0.08
    æłī
    -0.08
    æĻĶ
    -0.08
    æĺ¯å¯¹
    -0.08
    ynn
    -0.08
    ABCDEFG
    -0.08
    idia
    -0.08
    imal
    -0.08
    .sim
    -0.08
    å°ıåŃ©
    -0.08
    POSITIVE LOGITS
    å¥ĩå¦Ļ
    0.10
    éľ²
    0.09
    /out
    0.09
    oley
    0.09
    æĹłå£°
    0.09
    msp
    0.09
    éģ®
    0.08
    è¿ĺä¸įæĺ¯
    0.08
    åĭ¾
    0.08
    æķ´ä¸ª
    0.08
    Activations Density 0.127%

    No Known Activations