© 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. 26978
    Prev
    Next
    INDEX
    Explanations

    fortunately or luckily

    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
    ä¹į
    -0.10
    æ¾Į
    -0.09
    æģ³
    -0.09
    æĪIJè´¥
    -0.09
     бÑĭ
    -0.09
    æľŁæľĽ
    -0.09
    ÑĥÑĩа
    -0.08
    åĬ¿
    -0.08
    çĽ¼æľĽ
    -0.08
    ä»ĵ
    -0.08
    POSITIVE LOGITS
    ä¸įèĩ³äºİ
    0.14
    è¿ĺç®Ĺ
    0.11
    å¤Ł
    0.11
    è¶³å¤Ł
    0.10
     luckily
    0.10
     ÑĢаÑģпÑĢоÑģÑĤÑĢанен
    0.09
    æľīè¶³å¤ŁçļĦ
    0.09
    æĬ¢æķij
    0.09
     fortunately
    0.09
     doses
    0.09
    Activations Density 0.040%

    No Known Activations