© 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. 62725
    Prev
    Next
    INDEX
    Explanations

    names of doctors

    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¸īåĪĨ
    -0.09
    ä¸Ģç¬Ķ
    -0.08
    åħļåĴĮåĽ½å®¶
    -0.08
    ÑĢÑıд
    -0.08
    èĶ½
    -0.08
    <article
    -0.08
    erule
    -0.08
    éĻįèĩ³
    -0.08
    ensem
    -0.07
    arti
    -0.07
    POSITIVE LOGITS
    们çļĦ
    0.11
    obi
    0.10
    åIJįå¸Ī
    0.10
    èĮĥ
    0.09
    Ease
    0.09
    omo
    0.09
    ler
    0.08
    æīĭåĬ¨
    0.08
    以ä¸ĬçļĦ
    0.08
    æīĵä»Ĺ
    0.08
    Activations Density 0.011%

    No Known Activations