© 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. 37684
    Prev
    Next
    INDEX
    Explanations

    focusing on, identify exposure, makes a

    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
    åijĬè¯īä»ĸ
    -0.09
    åijĻ
    -0.09
    横
    -0.09
    纷纷表示
    -0.09
    _tl
    -0.09
    éĹ®éĹ®
    -0.08
    è°£
    -0.08
    arium
    -0.08
    åĨ
    -0.08
    åĽłä¸ºæĪij们
    -0.08
    POSITIVE LOGITS
    读èĢħ
    0.10
    äºĨä¸Ģç³»åĪĹ
    0.10
    ä»ĸçļĦ
    0.09
    å¨ĵ
    0.09
    举ä¾ĭ
    0.09
    è¯ĺ
    0.09
    ç»ĵå°¾
    0.09
    ä¸Ģç³»åĪĹ
    0.09
    æıIJåĩºäºĨ
    0.09
    æݨå´ĩ
    0.09
    Activations Density 0.106%

    No Known Activations