© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 19499
    Prev
    Next
    INDEX
    Explanations

    semiconductor laser

    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
    è¯ģåĪ¸äº¤æĺĵ
    -0.10
    onta
    -0.10
    åľ¨é¦Ļ港
    -0.10
    roof
    -0.10
    ç©·
    -0.10
    è§³
    -0.10
    éŃĶ鬼
    -0.09
    被æ·ĺæ±°
    -0.09
     Hub
    -0.09
    éļ¶å±ŀ
    -0.09
    POSITIVE LOGITS
    èĵĦ
    0.10
    ä¸Ģåı¥è¯Ŀ
    0.09
    пÑĥÑģ
    0.09
    forcer
    0.08
    èįī
    0.08
    建ç«ĭåģ¥åħ¨
    0.08
    arrow
    0.08
    ç͵åĬ¨
    0.08
     pomp
    0.08
    mus
    0.08
    Activations Density 0.204%

    No Known Activations