© 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. 27435
    Prev
    Next
    INDEX
    Explanations

    redevelopment agency and district financing

    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
    åıijå±ķæĸ¹åIJij
    -0.10
    家ä¸Ń
    -0.10
     ÑģÑĤоим
    -0.09
    åѦç§ij
    -0.09
    æĪij家
    -0.09
    æ³Ħéľ²
    -0.09
    éªij
    -0.09
    Licensed
    -0.09
    毡
    -0.09
    .diag
    -0.08
    POSITIVE LOGITS
    å¼Ģåıij建设
    0.11
    åľŁåľ°
    0.10
    æĭĨè¿ģ
    0.10
    å¹³æĸ¹åħ¬éĩĮ
    0.10
    æī©å®¹
    0.10
    ç½®æį¢
    0.10
    åŁİåĮº
    0.09
    ä¸Ńå¿ĥåŁİåĮº
    0.09
     baise
    0.09
    æľºåĪ¶
    0.09
    Activations Density 0.069%

    No Known Activations