© 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. 9307
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles

    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
    çĹĴ
    -0.09
    åħ³äºİæĪij们
    -0.09
    è¡Ķ
    -0.08
    央
    -0.08
    å¾ĹæĦı
    -0.08
    \/
    -0.08
     Urb
    -0.08
    å°ĨåĨĽ
    -0.08
    çļĦæĸ¹å¼ıæĿ¥
    -0.07
     Dick
    -0.07
    POSITIVE LOGITS
    说åĩºæĿ¥
    0.11
    .pref
    0.10
    念
    0.10
    æĥ³äºĨ
    0.10
    æķ´æķ´
    0.09
    è¶Ķ
    0.09
    <tbody
    0.09
    åł¡
    0.09
    GIN
    0.09
    说å®Į
    0.09
    Activations Density 0.350%

    No Known Activations