© 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. 37914
    Prev
    Next
    INDEX
    Explanations

    past followed by time unit

    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
    å½ĵæŶçļĦ
    -0.10
    å½ĵæŶ
    -0.10
    eva
    -0.09
     eventual
    -0.08
    ibur
    -0.08
    atories
    -0.08
     Sanford
    -0.08
    çķ¶æĻĤ
    -0.08
    éĵģè·¯
    -0.08
    åľ°å¤Ħ
    -0.08
    POSITIVE LOGITS
    åĩłå¤©
    0.12
    两年
    0.12
    åħļåĴĮåĽ½å®¶
    0.10
    çĿ£
    0.10
    åĩłå¹´
    0.10
    ä¸įä½ı
    0.09
    两天
    0.09
    ustum
    0.09
    äºĶæĺŁ
    0.09
    åįģå¹´
    0.09
    Activations Density 0.037%

    No Known Activations