© 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. 37608
    Prev
    Next
    INDEX
    Explanations

    measurement, rankings, average, index

    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
    riv
    -0.09
    京津
    -0.09
    ç½ķ
    -0.09
    æī¹åıijå¸Ĥåľº
    -0.09
    ampo
    -0.09
     CG
    -0.09
    åħ¨æĹ¥
    -0.09
    诲
    -0.09
    åĬŀåħ¬æ¥¼
    -0.09
    缴è¾ĸ
    -0.09
    POSITIVE LOGITS
    é«ĺ级
    0.10
    achi
    0.09
    å©
    0.09
    .fre
    0.09
    Enumerator
    0.09
     topLevel
    0.09
     açısından
    0.09
    æĮĩæķ°
    0.09
    æĮĩæłĩ
    0.09
     Freedom
    0.08
    Activations Density 0.048%

    No Known Activations