© 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. 52443
    Prev
    Next
    INDEX
    Explanations

    reference or citation

    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
    ä¼¼çļĦ
    -0.10
     Ñģог
    -0.10
    iena
    -0.10
    æį¢äºĨ
    -0.10
    æī°
    -0.09
    æĵ¾
    -0.09
    ä¸İåıijå±ķ
    -0.09
    .Formatter
    -0.09
    å®ŀè´¨æĢ§
    -0.09
    åĮ¿åIJį
    -0.09
    POSITIVE LOGITS
     [
    0.09
    åIJĮå¿Ĺ
    0.09
    鹤
    0.08
    isk
    0.08
    èĦį
    0.08
    èĢģèĻİ
    0.08
     appro
    0.08
    ä¸įè¿ľ
    0.08
    æĪ³
    0.07
    çĤ½
    0.07
    Activations Density 0.163%

    No Known Activations