© 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. 53032
    Prev
    Next
    INDEX
    Explanations

    rescue or save

    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
    ctor
    -0.09
    æ±ľ
    -0.09
    å¹´ä¹ĭä¹ħ
    -0.08
     TÆ°
    -0.08
    åĴĦ
    -0.08
    便åĪ©
    -0.08
    ä¸įåIJĥ
    -0.08
    妾
    -0.08
    说ä¸įåĩº
    -0.08
    _shot
    -0.08
    POSITIVE LOGITS
     rescue
    0.23
    æĭ¯æķij
    0.22
    æķij
    0.21
    æķijæı´
    0.21
    æķijåĬ©
    0.19
     Rescue
    0.17
     cứu
    0.17
     rescued
    0.16
     resc
    0.15
    æķij人
    0.15
    Activations Density 0.081%

    No Known Activations