© 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. 52910
    Prev
    Next
    INDEX
    Explanations

    professional, budget, or quality descriptors

    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
    èѦ
    -0.09
    æĭİ
    -0.09
    ft
    -0.09
    ä¹ĭæĺŁ
    -0.09
    uman
    -0.08
    çķĻåѦçĶŁ
    -0.08
    æĴ°
    -0.08
     Fre
    -0.08
    ä¹ĸä¹ĸ
    -0.08
    ISTS
    -0.08
    POSITIVE LOGITS
    çŃĸåĪĴ
    0.11
    äºĨä¸Ģåľº
    0.10
    çĽĽå¤§
    0.10
    ä¸ĵä¸ļ人士
    0.09
    æ°´åĩĨ
    0.09
    IBLE
    0.09
    æłĩåĩĨåĮĸ
    0.09
    å¤ļåªĴä½ĵ
    0.09
    è¾Ħ
    0.09
     polished
    0.09
    Activations Density 0.092%

    No Known Activations