© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4646
    Prev
    Next
    INDEX
    Explanations

    quota, allotment, bid, contract

    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
    æĬķèµĦåŁºéĩij
    -0.09
    室å¤ĸ
    -0.09
    åħ»æĪIJ
    -0.08
     Bere
    -0.08
    å¤ļæĸ¹
    -0.08
     акÑĤÑĥ
    -0.08
    ä¸įéĢĤåIJĪ
    -0.08
    çݺ
    -0.08
    CBD
    -0.08
    Suit
    -0.08
    POSITIVE LOGITS
    åIJįé¢Ŀ
    0.18
     quota
    0.13
    é¢Ŀ度
    0.12
    éĻIJéĩı
    0.11
    æĮĩæłĩ
    0.10
    åĪĨéħį
    0.10
    æľºåĬ¨
    0.10
    æľªå©ļ
    0.10
    空éĹ´
    0.10
    ä¹ĭåĨħ
    0.10
    Activations Density 0.067%

    No Known Activations