© 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. 9303
    Prev
    Next
    INDEX
    Explanations

    Lara, elle, odi, ara

    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
    ees
    -0.11
    eur
    -0.10
    åĬŁè¯¾
    -0.08
    åİ¢
    -0.08
    ToLocal
    -0.08
    igan
    -0.08
    imal
    -0.08
    é¥
    -0.08
    ted
    -0.08
    ØŃا
    -0.08
    POSITIVE LOGITS
    主æĦı
    0.10
    å¾ģæ±Ĥ
    0.09
    (strict
    0.09
    Ìģ
    0.09
    æ»Ł
    0.09
    enders
    0.08
    èݹ
    0.08
    /ion
    0.08
    åģ¥åº·äº§ä¸ļ
    0.08
    akra
    0.08
    Activations Density 0.012%

    No Known Activations