© 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. 21561
    Prev
    Next
    INDEX
    Explanations

    refrigerated / refrigerator / partitioning

    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
    ä¸ĢåĪ»
    -0.09
    éĿ¶
    -0.08
    ä¿Ĺ
    -0.08
    åı¦ä¸Ģç§į
    -0.08
    uition
    -0.08
     diff
    -0.08
     Dare
    -0.08
    another
    -0.08
    åħ¬çĦ¶
    -0.08
    è°ĥåĬ¨
    -0.08
    POSITIVE LOGITS
    颦
    0.09
    çĽ¸å¯¹è¾ĥ
    0.09
    ä¸Ńå°ı
    0.09
    å»Ł
    0.09
    åIJĨ
    0.09
    æ±²
    0.09
     вÑģÑİ
    0.09
    cente
    0.09
    åıįèħIJ
    0.09
    è§ģè¯ģäºĨ
    0.09
    Activations Density 0.014%

    No Known Activations