© 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. 51639
    Prev
    Next
    INDEX
    Explanations

    insufficient or sufficient quantities

    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
    æİı
    -0.10
    æĥ³åĪ°
    -0.09
    çļĦåĸľçĪ±
    -0.09
    积æŀģä½ľçĶ¨
    -0.09
    éĤ»éĩĮ
    -0.09
    å¿ĥ缮ä¸Ń
    -0.09
    对ä»ĸ们
    -0.09
    身价
    -0.09
    furt
    -0.09
    éģµå®Ī
    -0.08
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.19
     enough
    0.19
    è¶³å¤Ł
    0.18
    å¤Ł
    0.18
    å¤ł
    0.18
    ä¸į足
    0.18
    ä¸įå¤Ł
    0.17
     Enough
    0.16
    åħħ足
    0.16
    Enough
    0.16
    Activations Density 0.072%

    No Known Activations