© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10471
    Prev
    Next
    INDEX
    Explanations

    smart devices

    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
    è¹´
    -0.10
    -Pacific
    -0.09
    hape
    -0.09
     Gos
    -0.09
    âĩ¨
    -0.09
    å·±
    -0.08
     باÙĦÙĨ
    -0.08
    cis
    -0.08
    otron
    -0.08
    vern
    -0.08
    POSITIVE LOGITS
    åIJĪ约
    0.10
    ness
    0.09
    iff
    0.09
    est
    0.09
    为æ°ij
    0.09
    åĪ®
    0.09
    ä¹ĭ举
    0.09
    ulla
    0.09
    nels
    0.09
    prov
    0.09
    Activations Density 0.009%

    No Known Activations