© 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. 57758
    Prev
    Next
    INDEX
    Explanations

    right-wing activists and writers

    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
    åģľçīĮ
    -0.09
    olie
    -0.09
    åģİ
    -0.09
    æĦŁæħ¨
    -0.09
    æĦŁåı¹
    -0.09
    ollo
    -0.09
    æĦĽæĥħ
    -0.09
    èĤĩ
    -0.09
     hostages
    -0.08
    èĥ¥
    -0.08
    POSITIVE LOGITS
    åĨįçĶŁ
    0.10
    ä¼łæĴŃ
    0.10
    CLAIM
    0.10
    宣æī¬
    0.09
    宣讲
    0.09
    çħ½
    0.09
    èĩªç§°
    0.09
    称
    0.09
    pseudo
    0.09
    å®£ä¼ł
    0.09
    Activations Density 0.107%

    No Known Activations