© 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. 23039
    Prev
    Next
    INDEX
    Explanations

    quantum dots, nanocrystals

    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
    arer
    -0.09
    æ´®
    -0.09
    éĢ¼
    -0.09
    è¾°
    -0.08
    ARA
    -0.08
    vara
    -0.08
    ä¸įå¾Ĺå·²
    -0.08
    splice
    -0.08
    ADF
    -0.08
    fone
    -0.08
    POSITIVE LOGITS
    æŃĮ声
    0.10
    级åĪ«çļĦ
    0.10
     Dice
    0.10
    letcher
    0.09
    çĶ¸
    0.09
    -sizing
    0.09
    åıijçĥ§
    0.09
    è¾ħ导åijĺ
    0.09
    æĿľç»Ŀ
    0.08
    æĬĹæ°§åĮĸ
    0.08
    Activations Density 0.544%

    No Known Activations