© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8273
    Prev
    Next
    INDEX
    Explanations

    Gee`s, Black`s, Ferris`s

    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
    ycl
    -0.11
    ä¼Ĺ
    -0.10
    æīĪ
    -0.09
    lops
    -0.09
    subst
    -0.09
    ourg
    -0.09
    anon
    -0.09
    tü
    -0.08
    _SIMPLE
    -0.08
    ages
    -0.08
    POSITIVE LOGITS
    鲫
    0.10
    诤
    0.08
    询
    0.08
    èĦ¾æ°Ķ
    0.08
    å¿Ļ
    0.08
    åĽºçĦ¶
    0.08
    è¾Ĩ车
    0.08
    ç¾ŀ
    0.08
    iÅŁ
    0.08
    åĩºå¤Ħ
    0.08
    Activations Density 0.006%

    No Known Activations