© 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. 31402
    Prev
    Next
    INDEX
    Explanations

    be + past participle

    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
    æį®æѤ
    -0.10
    åīįæīĢæľªæľī
    -0.10
    å¦Ļ
    -0.09
    åı¯çĶ¨äºİ
    -0.09
    abad
    -0.09
    usage
    -0.09
    è¿ĺæĥ³
    -0.08
     Sad
    -0.08
     di
    -0.08
     usage
    -0.08
    POSITIVE LOGITS
    ä¹°åĪ°
    0.11
    åĩłåı¥
    0.10
    èĤłèĥĥ
    0.10
    è½»æĿ¾
    0.10
    ä¸Ģä¸ĭåŃIJ
    0.10
    ä¸Ģåı£
    0.09
    ç®Ģåįķ
    0.09
    åĬŀ好
    0.09
    reds
    0.09
    è½»æĺĵ
    0.09
    Activations Density 0.139%

    No Known Activations