© 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. 33129
    Prev
    Next
    INDEX
    Explanations

    profit and profits

    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
    ç»ĥ
    -0.09
    åĬ³
    -0.09
    å¤ļå±Ĥ次
    -0.09
    ç·´
    -0.08
    å¡Į
    -0.08
    éĽĨä¸Ń
    -0.08
     Kỳ
    -0.08
    ç»ĥä¹ł
    -0.08
    åģı离
    -0.08
    ITO
    -0.08
    POSITIVE LOGITS
     profit
    0.23
    åĪ©æ¶¦
    0.22
    çĽĪåĪ©
    0.20
     Profit
    0.18
     profits
    0.17
    Profit
    0.17
    æĶ¶çĽĬ
    0.16
    profit
    0.16
    ç»ıæµİæķĪçĽĬ
    0.16
     profitability
    0.15
    Activations Density 0.052%

    No Known Activations