© 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. 54398
    Prev
    Next
    INDEX
    Explanations

    containers and accessories

    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
    apia
    -0.10
    èĥ¸
    -0.09
    _TestCase
    -0.09
    _DISK
    -0.09
    culo
    -0.08
    åŀ©
    -0.08
    andal
    -0.08
     Tall
    -0.08
    æŁ¥å°ģ
    -0.08
    .useState
    -0.08
    POSITIVE LOGITS
    éĩĮ
    0.10
    裡
    0.09
    åĩłä¹İæīĢæľī
    0.09
    éĩĮçļĦ
    0.08
    å¯Ł
    0.08
    éħįæĸĻ
    0.08
    æĻ®åıĬ
    0.08
    oder
    0.08
    åIJij社ä¼ļ
    0.08
    解æĶ¾
    0.08
    Activations Density 0.026%

    No Known Activations