© 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. 48456
    Prev
    Next
    INDEX
    Explanations

    profit margins

    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
    çĽ¸äº²
    -0.11
    ä¸į失
    -0.09
    失ä¸ļ
    -0.09
    åħ¬æ°ij
    -0.09
    åıĮæīĭ
    -0.09
    轶
    -0.09
    çݯç»ķ
    -0.09
    epy
    -0.08
    æĶ¾å¿ĥ
    -0.08
    个人
    -0.08
    POSITIVE LOGITS
    åĪ©æ¶¦çİĩ
    0.21
    åĪ©æ¶¦
    0.19
    æ¯ĽåĪ©çİĩ
    0.18
     profit
    0.14
    çĽĪåĪ©èĥ½åĬĽ
    0.12
     Profit
    0.12
     margins
    0.12
    profit
    0.12
    -margin
    0.12
    Profit
    0.12
    Activations Density 0.060%

    No Known Activations