© 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. 19603
    Prev
    Next
    INDEX
    Explanations

    miss out or miss something

    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
    çĿĢæīĭ
    -0.09
    cmc
    -0.09
    erland
    -0.09
    éĻĦ件
    -0.09
    æģ¸
    -0.09
    elter
    -0.09
    tep
    -0.09
    飬
    -0.09
    å¹´ç»Ī
    -0.09
    짱
    -0.09
    POSITIVE LOGITS
    éĶĻè¿ĩ
    0.29
    éĶĻè¿ĩäºĨ
    0.29
     missed
    0.26
    miss
    0.18
    _miss
    0.16
    éģĹæ¼ı
    0.16
     misses
    0.16
    Miss
    0.15
     miss
    0.15
    缺å¸Ń
    0.15
    Activations Density 0.124%

    No Known Activations