© 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. 51714
    Prev
    Next
    INDEX
    Explanations

    microsoft office suite

    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
    è¡Įä¸ļåıijå±ķ
    -0.09
    wort
    -0.09
    缸åħ³æĸ°éĹ»
    -0.09
    éķIJ
    -0.09
     unreal
    -0.09
    åįĩ
    -0.09
    转弯
    -0.09
     Unreal
    -0.08
    BERS
    -0.08
    cript
    -0.08
    POSITIVE LOGITS
    åĬŀåħ¬
    0.09
    .microsoft
    0.08
     оÑĦ
    0.08
    ä¸įå®Į
    0.08
     suite
    0.08
     Masc
    0.08
    çĶ¨åĵģ
    0.08
    è²Ķ
    0.08
    宾客
    0.08
    ä¹ĭ家
    0.08
    Activations Density 0.036%

    No Known Activations