© 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. 7950
    Prev
    Next
    INDEX
    Explanations

    expressions with comma-separated lists

    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
    åĪ«è¯´
    -0.08
    æīįæĺ¯çľŁæŃ£
    -0.07
    âĢIJ
    -0.07
    amp
    -0.07
    9
    -0.07
     fringe
    -0.07
    6
    -0.07
    4
    -0.07
    åIJĦè¡Į
    -0.07
    æĪĸå¤ļæĪĸå°ij
    -0.07
    POSITIVE LOGITS
    欹
    0.11
    -BEGIN
    0.10
    bnb
    0.10
    æijĩäºĨ
    0.10
    ackbar
    0.10
    .SOCK
    0.09
    çŃ¾ä¸ĭ
    0.09
    婵
    0.09
    æŁ½
    0.09
    AAAAAAAA
    0.09
    Activations Density 0.106%

    No Known Activations