© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58963
    Prev
    Next
    INDEX
    Explanations

    groups of numbers (quartet, trio, trilogy)

    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
    inkel
    -0.08
    InstanceState
    -0.08
    çĶŁäº§æĢ»åĢ¼
    -0.08
     Rudd
    -0.08
    	sizeof
    -0.08
    peek
    -0.08
    few
    -0.07
    urgence
    -0.07
    udas
    -0.07
    åİ
    -0.07
    POSITIVE LOGITS
    ä¸Ģç»Ħ
    0.12
    é«ĺ楼
    0.10
    è¿Ļä¸ī个
    0.10
    /qu
    0.10
    æĪĸå¤ļ
    0.10
    remen
    0.10
    çĻ½æ²Ļ
    0.10
    dzi
    0.09
    ا
    0.09
    ç»Ħéķ¿
    0.09
    Activations Density 0.032%

    No Known Activations