© 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. 8984
    Prev
    Next
    INDEX
    Explanations

    .co followed by country code

    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
    è¢ħ
    -0.08
     McCorm
    -0.08
     ê·¸ëłĩì§Ģ
    -0.08
    ç¿°
    -0.08
    ãĥIJãĤ¹
    -0.08
    åĬ©
    -0.08
    å¸ĤæķĻèĤ²
    -0.08
    ä¹IJæĦı
    -0.08
    åľ¨çĶŁæ´»ä¸Ń
    -0.08
    ght
    -0.08
    POSITIVE LOGITS
    .uk
    0.12
    semb
    0.10
     minded
    0.08
    oby
    0.08
    å·®çĤ¹
    0.08
    alli
    0.08
    å¢ĥ
    0.08
    ignment
    0.08
    _ctl
    0.08
    éķĽ
    0.08
    Activations Density 0.012%

    No Known Activations