© 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. 21111
    Prev
    Next
    INDEX
    Explanations

    efforts and recovery operations

    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
    累累
    -0.10
    æīĢéľĢè¦ģ
    -0.10
    缸åħ³ä¿¡æģ¯
    -0.09
    éŀŃ
    -0.09
    дей
    -0.09
    .toolbox
    -0.09
    angu
    -0.08
    ä¸Ģä¸ĭåŃIJå°±
    -0.08
     PIO
    -0.08
    CEE
    -0.08
    POSITIVE LOGITS
     efforts
    0.32
    çļĦåĬªåĬĽ
    0.27
     effort
    0.27
    åĬªåĬĽ
    0.27
     attempts
    0.22
     ÑĥÑģили
    0.21
     attempt
    0.18
     Eff
    0.18
     ëħ¸ëł¥
    0.17
    _attempts
    0.16
    Activations Density 0.309%

    No Known Activations