© 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. 34133
    Prev
    Next
    INDEX
    Explanations

    wind and breeze direction

    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
    è¾īçħĮ
    -0.09
    äºĮ代
    -0.09
    æ³ħ
    -0.09
    åĭĭ
    -0.09
    åĭ
    -0.09
    å¿ĥ缮ä¸Ń
    -0.09
    群éĩĮ
    -0.09
    è¹ĭ
    -0.09
    åĴĦ
    -0.08
    åı±
    -0.08
    POSITIVE LOGITS
    é£İ
    0.24
     wind
    0.21
    風
    0.21
    é£İåIJ¹
    0.20
     winds
    0.20
     breeze
    0.18
    wind
    0.18
     Winds
    0.17
    Wind
    0.16
    é£İåı£
    0.16
    Activations Density 0.044%

    No Known Activations