© 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. 53814
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
    äºĨäºĽ
    -0.09
    æľīä¸ĢçĤ¹
    -0.09
    æľī个
    -0.09
    顺
    -0.09
    鸬
    -0.09
     Orchard
    -0.08
    æ¶Īæŀģ
    -0.08
    ecom
    -0.08
    pas
    -0.08
    dyn
    -0.08
    POSITIVE LOGITS
    çĽ²
    0.12
    æİī
    0.10
    yen
    0.09
    ifax
    0.09
    iets
    0.09
    çľł
    0.09
    å¨ģæħij
    0.09
    è®´
    0.09
    å³°åĢ¼
    0.08
    带åĪ°
    0.08
    Activations Density 0.414%

    No Known Activations