© 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. 11663
    Prev
    Next
    INDEX
    Explanations

    when followed by you or it

    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
     каÑĩ
    -0.10
    åģ¥åħ¨
    -0.09
    pha
    -0.08
    æĮł
    -0.08
    gel
    -0.08
     Kale
    -0.08
    åĩłåįĥ
    -0.08
    others
    -0.08
    宸
    -0.08
    Premium
    -0.08
    POSITIVE LOGITS
    æ¶īåıĬåĪ°
    0.11
    渲
    0.10
    ÑĮÑİ
    0.09
    åij¤
    0.09
    èĦĤ
    0.09
    èĩ³äºİ
    0.09
    Invoker
    0.09
    èĢĥèĻijåĪ°
    0.09
    éĿ¢å¯¹
    0.09
    å·©
    0.09
    Activations Density 0.055%

    No Known Activations