© 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. 37147
    Prev
    Next
    INDEX
    Explanations

    total measurement components

    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
    á»ĩ
    -0.09
    å¼Ń
    -0.08
    icamente
    -0.08
    ultz
    -0.08
     Cul
    -0.08
    Alternate
    -0.08
    iece
    -0.08
    _portal
    -0.08
     Consortium
    -0.08
    inine
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪĩ
    0.11
    æı©
    0.09
    .asp
    0.09
    循
    0.09
    ä¸Ĭåİ»
    0.09
    stä
    0.09
    ufe
    0.09
    夫人
    0.09
    社ä¼ļæķĪçĽĬ
    0.09
    ÄIJT
    0.09
    Activations Density 0.048%

    No Known Activations