© 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. 36655
    Prev
    Next
    INDEX
    Explanations

    one in X ratio

    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
     breath
    -0.10
     Cruise
    -0.09
     bre
    -0.08
    Vis
    -0.08
    æĺ¥èĬĤ
    -0.08
    åij¼åIJ¸
    -0.08
    afil
    -0.08
    IDL
    -0.08
    ç´§å¼ł
    -0.08
    éĽĨèģļ
    -0.08
    POSITIVE LOGITS
    èĢĮåİ»
    0.10
    åĵĢ
    0.09
    裳
    0.09
    è¯Ħè®®
    0.09
    å¾®å¦Ļ
    0.09
    笺
    0.09
     пÑĢоизводÑģÑĤва
    0.09
    éĺŁéķ¿
    0.09
    _ratings
    0.09
    vak
    0.09
    Activations Density 0.030%

    No Known Activations