© 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. 39271
    Prev
    Next
    INDEX
    Explanations

    air conditioning

    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
    对çŃĸ
    -0.10
    äºı
    -0.09
    legacy
    -0.09
    vat
    -0.09
    åı¯æĥ³
    -0.09
    ç£ħ
    -0.09
    æĸ¹åIJijçĽĺ
    -0.09
    éĩįè§Ĩ
    -0.09
    åħ¢
    -0.08
    éģĹçķĻ
    -0.08
    POSITIVE LOGITS
    è¿Ļ个æĹ¶ä»£
    0.09
    丰满
    0.09
    讽
    0.08
     caps
    0.08
    ç¨įç¨į
    0.08
    ä»ħ代表
    0.08
    饱满
    0.08
    å¤ļæł·åĮĸ
    0.08
    èı±
    0.08
    IDES
    0.08
    Activations Density 0.009%

    No Known Activations