© 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. 9417
    Prev
    Next
    INDEX
    Explanations

    of them

    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
    2
    -0.10
    zl
    -0.09
    3
    -0.09
    9
    -0.09
    8
    -0.09
    4
    -0.09
    5
    -0.08
    6
    -0.08
    7
    -0.08
    åįģåĩłä¸ª
    -0.08
    POSITIVE LOGITS
     ниÑħ
    0.16
    å®ĥ
    0.14
    å®ĥ们
    0.13
     него
    0.12
     them
    0.12
     ones
    0.12
    åħ¶ä¸Ńæľī
    0.12
    è¯Ŀ说
    0.11
    å®ĥåı¯ä»¥
    0.11
    äºĮèĢħ
    0.11
    Activations Density 0.062%

    No Known Activations