© 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. 62710
    Prev
    Next
    INDEX
    Explanations

    ending or leaving

    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
    å·®çĤ¹
    -0.10
    宥
    -0.08
    éĹ»
    -0.08
     Boone
    -0.08
    tain
    -0.08
    å¢ħ
    -0.08
    éĴŀ
    -0.08
     trì
    -0.08
    é«®
    -0.08
    ä¿ı
    -0.08
    POSITIVE LOGITS
    çļĦåħ´è¶£
    0.10
    åī©ä¸ĭçļĦ
    0.10
    åī©ä¸ĭ
    0.10
    åĽŀåİ»
    0.10
     над
    0.09
    eward
    0.09
    ĶåĽŀ
    0.09
    åħ´è¶£
    0.09
    åŁĤ
    0.09
     Gone
    0.09
    Activations Density 0.154%

    No Known Activations