© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7705
    Prev
    Next
    INDEX
    Explanations

    decided to

    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
    MOTE
    -0.09
    æī¯
    -0.09
    æİ¥èijĹ
    -0.09
    Ñĭва
    -0.08
    ghi
    -0.08
    -spe
    -0.08
    èĻŀ
    -0.08
    atching
    -0.08
    æİ¥çĿĢ
    -0.08
    soon
    -0.08
    POSITIVE LOGITS
     rằng
    0.10
    åĨįä¹Łæ²¡æľī
    0.10
    æķĪ
    0.10
    éĵ¤
    0.09
    æĺ¥èĬĤæľŁéĹ´
    0.09
    èħ°éĥ¨
    0.09
    è¿Ļå°±æĺ¯
    0.08
    æijĪ
    0.08
    临
    0.08
    ahn
    0.08
    Activations Density 0.022%

    No Known Activations