© 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. 8085
    Prev
    Next
    INDEX
    Explanations

    interest rate percentage

    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
    åĿ¨
    -0.09
    é¢Ħè§ģ
    -0.09
    çĨŁçŁ¥
    -0.09
    çĻ½äºij
    -0.08
    onet
    -0.08
    çķ´
    -0.08
    è¾ĵäºĨ
    -0.08
    两类
    -0.08
    irm
    -0.08
    firm
    -0.08
    POSITIVE LOGITS
    çİĩ
    0.14
    çİĩ为
    0.13
    çİĩè¾¾
    0.11
     rates
    0.11
     Rates
    0.11
    ë¥ł
    0.11
    çİĩè¾¾åĪ°
    0.10
    ìľ¨
    0.10
    .rate
    0.10
    rate
    0.10
    Activations Density 0.182%

    No Known Activations