© 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. 35842
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation

    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
    椿
    -0.09
    ãĤĪãģĨãģ§
    -0.08
    åĨ¤
    -0.08
    迸
    -0.08
    åľ¨å®¶éĩĮ
    -0.08
    çī¯
    -0.08
     fus
    -0.08
    æѤæĸĩ
    -0.07
    çļĦçłĶ究
    -0.07
    5
    -0.07
    POSITIVE LOGITS
    iams
    0.12
    enny
    0.10
    -spacing
    0.10
    Cheap
    0.09
    BACK
    0.09
    åºķæ°Ķ
    0.09
    WRAPPER
    0.09
    mins
    0.09
    éĺ¶æ¢¯
    0.09
    æĹĹä¸ĭçļĦ
    0.09
    Activations Density 0.091%

    No Known Activations