© 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. 23880
    Prev
    Next
    INDEX
    Explanations

    Donald Trump

    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
    UGE
    -0.11
    åĵįèµ·
    -0.10
    cloth
    -0.10
    汨
    -0.09
    ibri
    -0.09
    anst
    -0.09
    edly
    -0.08
    åıijæī¬
    -0.08
     Lind
    -0.08
    à¸ļาย
    -0.08
    POSITIVE LOGITS
    å¤ķéĺ³
    0.08
    æīĭä¸ĭ
    0.08
    bject
    0.08
    å®ĺåı¸
    0.08
    ä¹IJåĽŃ
    0.08
     Penguins
    0.08
    æĹĹå¸ľ
    0.08
     Reality
    0.08
    ayers
    0.08
    anity
    0.08
    Activations Density 0.018%

    No Known Activations