© 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. 51630
    Prev
    Next
    INDEX
    Explanations

    double-click and install

    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
    æĿ¥çľĭ
    -0.10
    æħİ
    -0.09
    ahi
    -0.09
    decor
    -0.09
    æĹłåĬ©
    -0.09
    æĨº
    -0.08
     Pence
    -0.08
    mouseout
    -0.08
    åıĪä¸Ģ次
    -0.08
    mdir
    -0.08
    POSITIVE LOGITS
    æĶ¾åľ¨
    0.10
    大éĥ¨åĪĨ人
    0.10
    æĶ¾åĪ°
    0.10
    å°ıçĻ½
    0.10
    æ´»ä¸ĭåİ»
    0.10
    æijĨåľ¨
    0.09
    .sig
    0.09
    åIJ¬è¯¾
    0.09
    èIJ½åľ°
    0.09
    à¸Ļาม
    0.09
    Activations Density 0.155%

    No Known Activations