© 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. 38165
    Prev
    Next
    INDEX
    Explanations

    someday

    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
    å½ĵæŶ
    -0.10
    å·²ç»ıå¼Ģå§ĭ
    -0.10
    à¸Ľà¸£à¸°
    -0.09
    è¿Ħä»Ĭ为æŃ¢
    -0.09
    åĩłå®¶
    -0.09
    å¼Ģ端
    -0.08
    åīįæīĢæľªæľī
    -0.08
    ensed
    -0.08
    оÑı
    -0.08
    æĺİ天
    -0.08
    POSITIVE LOGITS
    oming
    0.09
    ìĶ©
    0.09
    arias
    0.09
    媳å¦ĩ
    0.09
    æľīä¸Ģ天
    0.09
    iosis
    0.09
    ipers
    0.09
    ÑĢÑı
    0.08
     certain
    0.08
    dess
    0.08
    Activations Density 0.012%

    No Known Activations