© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52712
    Prev
    Next
    INDEX
    Explanations

    prepositions and article before nouns

    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
    iesel
    -0.10
    主人åħ¬
    -0.10
    .toObject
    -0.09
    çĻ½èī²
    -0.09
    å¥
    -0.09
    çıī
    -0.09
    $LANG
    -0.09
    _cookie
    -0.09
    æ´¾
    -0.09
    åİĭæĬij
    -0.09
    POSITIVE LOGITS
    äºĶæĺŁ
    0.10
    nist
    0.09
    5
    0.09
    4
    0.08
    æµ·åºķ
    0.08
     rogue
    0.08
    licas
    0.08
    2
    0.08
    rox
    0.08
    uls
    0.08
    Activations Density 0.018%

    No Known Activations