© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33044
    Prev
    Next
    INDEX
    Explanations

    number of

    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
     Shooter
    -0.10
    åį¿
    -0.09
    edo
    -0.09
    ä¸Ģç§Ĵ
    -0.09
    ÑĦиз
    -0.09
    جة
    -0.08
    æѧ
    -0.08
    zee
    -0.08
    .pad
    -0.08
    ingu
    -0.08
    POSITIVE LOGITS
     number
    0.26
     amount
    0.23
    æķ°éĩı
    0.21
    number
    0.21
     колиÑĩеÑģÑĤво
    0.19
    amount
    0.18
    NumberOf
    0.18
    à¸Īำà¸Ļวà¸Ļ
    0.17
     aantal
    0.17
    æķ°çĽ®
    0.17
    Activations Density 0.148%

    No Known Activations