© 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. 18550
    Prev
    Next
    INDEX
    Explanations

    Leonardo DiCaprio or Leo

    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
    buster
    -0.12
    å¾Ĺèµ·
    -0.09
    à¹ģ
    -0.09
    æľīåĬĽ
    -0.09
    enheim
    -0.08
    ively
    -0.08
    rail
    -0.08
    èĵ¼
    -0.08
    Ñıд
    -0.08
    vrier
    -0.08
    POSITIVE LOGITS
    é«ĺçļĦ
    0.10
    qed
    0.09
    iros
    0.09
    æİĴæ°Ķ
    0.08
    cond
    0.08
    ä»ĸæĺ¯ä¸Ģ个
    0.08
    æĬī
    0.08
    COND
    0.08
     assistants
    0.08
    rights
    0.08
    Activations Density 0.004%

    No Known Activations