© 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. 20750
    Prev
    Next
    INDEX
    Explanations

    doorways and entrances

    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
    ä¸įæŃ¢
    -0.09
    为主
    -0.09
    tha
    -0.09
    оз
    -0.08
    为主è¦ģ
    -0.08
    arus
    -0.08
    æĤ£
    -0.08
    æŀĦ件
    -0.08
    .datasource
    -0.08
    èı©èIJ¨
    -0.08
    POSITIVE LOGITS
    åıijå¸ĥäºĨ
    0.10
    æĸ°ä¸Ģè½®
    0.10
    æĹģ
    0.10
    ingleton
    0.10
    åĪļæīį
    0.09
    çĶ«
    0.09
    è¿ĻæŶ
    0.09
    rome
    0.09
    æݨåĩºäºĨ
    0.09
    åĹĴ
    0.09
    Activations Density 0.035%

    No Known Activations