© 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. 19568
    Prev
    Next
    INDEX
    Explanations

    day followed by common 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
    ORIES
    -0.10
    æµIJ
    -0.09
    å¸ij
    -0.09
    orie
    -0.09
    è¿Ļä¸ĢåĪ»
    -0.08
     днÑı
    -0.08
    åįĬæľĪ
    -0.08
    ories
    -0.08
    atte
    -0.08
    å°ıå¿ĥ
    -0.08
    POSITIVE LOGITS
    tempt
    0.09
    æ²»çĹħ
    0.08
    infeld
    0.08
    æľ¨è´¨
    0.08
    幺
    0.08
    干活
    0.08
    tant
    0.08
    sed
    0.08
    èĸ°
    0.08
    anic
    0.08
    Activations Density 0.008%

    No Known Activations