© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35547
    Prev
    Next
    INDEX
    Explanations

    money and investment terms

    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
    -0.09
    .construct
    -0.08
    adas
    -0.08
    æĪ¡
    -0.08
    éŃĤ
    -0.08
    esy
    -0.08
    åĨľåī¯
    -0.08
    çķħ
    -0.08
    READY
    -0.08
     ext
    -0.08
    POSITIVE LOGITS
    ä¸įçĶ¨
    0.10
    åıįè¿ĩæĿ¥
    0.10
    积累äºĨ
    0.09
    æľĢå¿«çļĦ
    0.09
    ä¸įå¿ħ
    0.09
    æ²¼
    0.09
     Inv
    0.09
     пÑĢоÑĨ
    0.09
    天æĸĩ
    0.09
     college
    0.09
    Activations Density 0.059%

    No Known Activations