© 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. 39665
    Prev
    Next
    INDEX
    Explanations

    carry / carried / carries

    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
    éĿ´
    -0.09
    stå
    -0.09
    æ¾Ħæ¸ħ
    -0.09
    åŬ
    -0.09
    ibox
    -0.09
    æĻĴ
    -0.09
    ached
    -0.08
    çŁ£
    -0.08
    ä¿Ł
    -0.08
    nar
    -0.08
    POSITIVE LOGITS
     carry
    0.12
    carry
    0.11
     carried
    0.11
    带åĪ°
    0.10
    åħ¨åľº
    0.10
    åĮħ袱
    0.09
     carrying
    0.09
     carries
    0.09
    çĺ¤
    0.09
    èĤ©
    0.09
    Activations Density 0.053%

    No Known Activations