© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50612
    Prev
    Next
    INDEX
    Explanations

    write about

    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
    SSIP
    -0.10
    ÑĪа
    -0.09
    褰
    -0.09
    çĨŁæĤī
    -0.09
    TimeString
    -0.09
    çłĶ讨
    -0.09
    éģĬãģ³
    -0.09
    .TabStop
    -0.09
    éĺį
    -0.09
    好åĥı
    -0.09
    POSITIVE LOGITS
     Dale
    0.12
    çĶ
    0.09
     Danielle
    0.09
    çķĽ
    0.08
    åĨ·
    0.08
    Dal
    0.08
    纲
    0.08
    ä¸įçĽ¸ä¿¡
    0.08
    æĬĢ
    0.08
    Utility
    0.08
    Activations Density 0.054%

    No Known Activations