© 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. 9196
    Prev
    Next
    INDEX
    Explanations

    question starter words (is, do, why, would)

    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
    çĮĹ
    -0.09
    eon
    -0.09
    å®Ļ
    -0.08
    bies
    -0.08
     Mam
    -0.08
     ÐĽÑİ
    -0.08
    _spawn
    -0.08
    iling
    -0.08
    笺
    -0.08
    è¾ĺ
    -0.07
    POSITIVE LOGITS
    è¿ĽèĢĮ
    0.09
    让å®ĥ
    0.09
    getInt
    0.09
    åij¨è½¬
    0.09
    梳
    0.09
    çݯèĬĤ
    0.09
    æĪĸå°Ĩ
    0.09
    ãģĤãĤĭãģĦãģ¯
    0.09
    æľªæĿ¥åıijå±ķ
    0.09
    upe
    0.09
    Activations Density 0.212%

    No Known Activations