© 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. 7722
    Prev
    Next
    INDEX
    Explanations

    center and centre

    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
    emark
    -0.10
    áĢĨ
    -0.10
    ä¸ŃæĸŃ
    -0.09
    ition
    -0.09
    enstein
    -0.09
    sst
    -0.09
    sson
    -0.09
    æ©IJ
    -0.09
    sky
    -0.08
    itional
    -0.08
    POSITIVE LOGITS
    pieces
    0.11
     вним
    0.11
    wise
    0.10
    åľ°å¸¦
    0.10
    prises
    0.10
    è¾ĺ
    0.10
    oids
    0.10
    ë§ģ
    0.10
    ial
    0.10
    less
    0.09
    Activations Density 0.094%

    No Known Activations