© 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. 37962
    Prev
    Next
    INDEX
    Explanations

    last thing or place

    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
    娱
    -0.09
    ç´§æī£
    -0.09
     ast
    -0.09
    çķĻåѦ
    -0.09
    ä¸įè¿ľå¤Ħ
    -0.09
    缴è¾ĸ
    -0.09
    æľīæĦı
    -0.09
    å±Ĥåĩº
    -0.08
    å¼ķæµģ
    -0.08
    ä¸įçķĻ
    -0.08
    POSITIVE LOGITS
    åł¡åŀĴ
    0.13
    æĬµæĬĹ
    0.13
    éĺµåľ°
    0.12
    æĬĹæĭĴ
    0.11
    对æĬĹ
    0.11
     bast
    0.11
    顽强
    0.10
    åѤ
    0.10
    å£ģåŀĴ
    0.10
    èIJ½
    0.10
    Activations Density 0.089%

    No Known Activations