© 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. 37877
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases and relative clauses

    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
    åŃ°
    -0.10
    å¾Ĭ
    -0.10
    åĵªä¸Ģ个
    -0.10
    åŁºéĩij份é¢Ŀ
    -0.10
    åĬŁè¯¾
    -0.10
    åĩłåIJį
    -0.09
     обÑıзан
    -0.09
    åī¯éĻ¢éķ¿
    -0.09
    è¿Ļåĩłä¸ª
    -0.09
    ç¼ł
    -0.09
    POSITIVE LOGITS
     mate
    0.09
     official
    0.08
    iba
    0.08
    å·¦åı³
    0.08
    erez
    0.08
     suit
    0.08
    mate
    0.07
    official
    0.07
    å»ī
    0.07
     beck
    0.07
    Activations Density 0.216%

    No Known Activations