© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51799
    Prev
    Next
    INDEX
    Explanations

    earphones or wing

    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
    vrier
    -0.09
    ffi
    -0.09
    acre
    -0.09
    estro
    -0.09
     Psi
    -0.09
    oppel
    -0.09
    èIJİ
    -0.09
    åĺ´å·´
    -0.09
     Alive
    -0.09
    æĸ°è¥¿
    -0.09
    POSITIVE LOGITS
    oman
    0.12
    çıij
    0.09
    åºŁæ°´
    0.09
    yu
    0.09
    ctic
    0.09
    ä¸įéĻIJ
    0.09
    deen
    0.09
    avo
    0.09
    ault
    0.08
    è¢Ĥ
    0.08
    Activations Density 0.002%

    No Known Activations