© 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. 2066
    Prev
    Next
    INDEX
    Explanations

    camera formats and accessories

    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
    å¾Ĥ
    -0.13
    æĴŃæĬ¥
    -0.09
     dise
    -0.09
    æĩ¿
    -0.09
     GIR
    -0.08
    <Unit
    -0.08
    åįķ项
    -0.08
    æĹ©çĤ¹
    -0.08
    åĬŁåĬĽ
    -0.08
    pond
    -0.08
    POSITIVE LOGITS
    åħĭ
    0.09
    ÑĢÑĥÑĩ
    0.09
    ä»ķ
    0.09
    严
    0.09
    åĶ®åIJİ
    0.09
    ensch
    0.08
    认
    0.08
     mah
    0.08
    æĿĥå¨ģ
    0.08
    ìłķ
    0.08
    Activations Density 0.004%

    No Known Activations