© 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. 38533
    Prev
    Next
    INDEX
    Explanations

    pound sterling prices

    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
    æľīå¾Ī大çļĦ
    -0.09
     Alaska
    -0.09
    åĪ¶åĵģ
    -0.09
     Minds
    -0.08
    第ä¸Ģéĥ¨
    -0.08
    ä¸Ģéĥ¨
    -0.08
    ummies
    -0.08
    åĬ©æīĭ
    -0.08
     Lester
    -0.08
    èķŀ
    -0.08
    POSITIVE LOGITS
     Camel
    0.09
    纲
    0.09
    chemes
    0.09
    åį¢
    0.09
    æĬij
    0.09
    agu
    0.09
    å¸ĪèĮĥ
    0.09
    ä¸įéĢĤ
    0.08
    æµĬ
    0.08
    çĪµå£«
    0.08
    Activations Density 0.024%

    No Known Activations