© 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. 39022
    Prev
    Next
    INDEX
    Explanations

    realize, realizing, realized

    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
    ening
    -0.11
    èµĦæĸĻæĺ¾ç¤º
    -0.10
    å®ŀè´¨æĢ§
    -0.10
    REA
    -0.09
    èĻ±
    -0.09
    大家åĪĨ享
    -0.09
     dau
    -0.09
    맨
    -0.09
    erson
    -0.09
    æĪijçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    éªĸ
    0.10
    稿
    0.10
    ationship
    0.09
    å¿ĥ头
    0.09
    æľīå¿ħè¦ģ
    0.09
    ably
    0.09
    ocket
    0.09
     rÃłng
    0.09
    æѤåĪ»
    0.09
    èĤ©è´Ł
    0.09
    Activations Density 0.011%

    No Known Activations