© 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. 21014
    Prev
    Next
    INDEX
    Explanations

    interest rate

    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
    çĭ¬åħ·
    -0.08
    ä¸ĵåĮº
    -0.08
    大åĬĽ
    -0.08
    ä¸ĢäºĮ
    -0.08
    èµ°åĩºæĿ¥
    -0.08
    ä¸ĸè´¸
    -0.08
    è´Łèį·
    -0.08
    gross
    -0.08
    steller
    -0.08
     ext
    -0.08
    POSITIVE LOGITS
    åŃ³
    0.17
    åĪ©æģ¯
    0.16
     interest
    0.14
    åĪ©çİĩ
    0.14
    interest
    0.14
     Interest
    0.13
    Interest
    0.13
    _interest
    0.13
    åŃ½
    0.13
    -interest
    0.12
    Activations Density 0.049%

    No Known Activations