© 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. 55749
    Prev
    Next
    INDEX
    Explanations

    assisted synthesis, Journal of, crete spacers, ive versus

    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
    å¿łå®ŀ
    -0.12
    æĮ«
    -0.10
    çĭłæĬĵ
    -0.10
    åī²
    -0.09
     dro
    -0.09
    ãģ£ãģ
    -0.09
    æł¹æºIJ
    -0.09
    å¤ĸçķĮ
    -0.08
    çĥŃæĥħ
    -0.08
    acia
    -0.08
    POSITIVE LOGITS
    åĬłçĽĸ
    0.10
    æıŃ
    0.10
    èŀį
    0.09
    çħ³
    0.09
    çħ§å°Ħ
    0.09
    åĴ¨
    0.09
    èĢIJ
    0.08
    åѤ
    0.08
    鸳
    0.08
    rees
    0.08
    Activations Density 0.022%

    No Known Activations