© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36633
    Prev
    Next
    INDEX
    Explanations

    content marketing

    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
    rant
    -0.10
    å®ļäºĨ
    -0.09
    ä½ķåĨµ
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    è´Ŀ壳
    -0.09
    èĩ¾
    -0.09
    ContentType
    -0.08
    adm
    -0.08
    åŃIJéĩĮ
    -0.08
    秽
    -0.08
    POSITIVE LOGITS
    æѤæĸĩ
    0.10
    ä¸įå¿į
    0.10
    aceous
    0.09
    æĹ¶è¡¨ç¤º
    0.09
    ually
    0.09
    ogan
    0.09
    oggle
    0.09
    ary
    0.08
    -divider
    0.08
    åħ¬ç§¯
    0.08
    Activations Density 0.030%

    No Known Activations