© 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. 11084
    Prev
    Next
    INDEX
    Explanations

    interest rates and pricing

    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
    ç³Ĭ
    -0.10
    éĥ¦
    -0.10
    arp
    -0.09
    éĵĨ
    -0.09
     Ñĥни
    -0.08
    è¢ĭ
    -0.08
    _fp
    -0.08
    æķĻèĤ²åŁ¹è®Ń
    -0.08
    æķ°åŃĹåĮĸ
    -0.08
    éªĮæĶ¶
    -0.08
    POSITIVE LOGITS
    éĻį
    0.15
    åĪ©çİĩ
    0.15
    éĻįåĪ°
    0.11
    åĪ©æģ¯
    0.11
     lãi
    0.10
    éĻįèĩ³
    0.10
    éĻįä½İäºĨ
    0.10
    æģ¯
    0.10
    åİĨåı²æĸ°
    0.09
     rates
    0.09
    Activations Density 0.032%

    No Known Activations