© 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. 61298
    Prev
    Next
    INDEX
    Explanations

    Arab and Arabic

    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
    manship
    -0.10
    agers
    -0.10
    æĦĨ
    -0.09
    ainty
    -0.09
    æīĭä¸Ĭ
    -0.09
    ager
    -0.09
    alty
    -0.09
    arp
    -0.09
    iveness
    -0.09
    ä¼ĹæīĢ
    -0.09
    POSITIVE LOGITS
    ely
    0.11
    æĺ¶
    0.11
    驾驶åijĺ
    0.10
    keit
    0.09
    igel
    0.09
     маÑĪ
    0.09
    .mvp
    0.09
    åĮķ
    0.09
    寤
    0.08
    ELY
    0.08
    Activations Density 0.024%

    No Known Activations