© 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. 8157
    Prev
    Next
    INDEX
    Explanations

    almost all

    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
    ãģĵãģĿ
    -0.10
    å·´å·´
    -0.09
    çĭĹ
    -0.09
    edImage
    -0.09
    èħĭ
    -0.08
    æĸŁ
    -0.08
    assis
    -0.08
    æŀľ
    -0.08
    äºĨå¤ļå°ij
    -0.08
    -era
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³
    0.11
    ä¹ĥèĩ³
    0.10
    æįŁ
    0.10
    NING
    0.09
    夤
    0.09
    ä¸İæѤ
    0.08
    çĶļèĩ³æĺ¯
    0.08
    ellers
    0.08
    åİŁåĪĻä¸Ĭ
    0.08
    bing
    0.08
    Activations Density 0.026%

    No Known Activations