© 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. 52501
    Prev
    Next
    INDEX
    Explanations

    welcoming and inviting guests

    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
    æĪ´çĿĢ
    -0.10
    éĩįè¦ģ
    -0.09
    æĪ´
    -0.09
    å¾Ĺ天
    -0.09
    .opensource
    -0.09
    avo
    -0.09
    mia
    -0.09
    åĿļå®ļä¸į
    -0.09
    èıĺ
    -0.09
     ÑĢем
    -0.09
    POSITIVE LOGITS
    æݥ纳
    0.10
    æĢģ度
    0.09
    ä¸ĩ家
    0.09
    liness
    0.09
    åºŁ
    0.09
    ly
    0.09
    endar
    0.09
    éĴĩ
    0.08
    antha
    0.08
    èĪĴ
    0.08
    Activations Density 0.007%

    No Known Activations