© 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. 3879
    Prev
    Next
    INDEX
    Explanations

    being followed by a descriptive phrase

    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
    ä¼ļä¸Ĭ
    -0.09
     bef
    -0.09
    ä¿¡èµĸ
    -0.08
     Vaugh
    -0.08
    被çĽĹ
    -0.08
    the
    -0.08
     Edison
    -0.08
    gregate
    -0.08
    çĽĺ
    -0.08
    ixa
    -0.07
    POSITIVE LOGITS
    rou
    0.11
    forth
    0.10
    åĿıäºĭ
    0.09
    ä¸ĸçķĮè§Ĥ
    0.08
    åģļçļĦäºĭ
    0.08
    è¡Įä¸ļåıijå±ķ
    0.08
    åģļæĪIJ
    0.08
    åĽºå®ļçļĦ
    0.08
    好çľĭçļĦ
    0.08
    äºĭæĥħ
    0.08
    Activations Density 0.032%

    No Known Activations