© 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. 47978
    Prev
    Next
    INDEX
    Explanations

    -ing verbs followed by prepositions

    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
    好åĥıæĺ¯
    -0.10
    LowerCase
    -0.09
    稳
    -0.09
    å°Ĩæĺ¯
    -0.09
    ilion
    -0.09
    æħ°
    -0.09
    lsi
    -0.09
     counter
    -0.09
    çī¹æľĹ
    -0.08
    家çĶ¨
    -0.08
    POSITIVE LOGITS
    ola
    0.09
    åħ°
    0.08
    稿
    0.08
    磷éħ¸
    0.08
     Spoon
    0.08
    æķ·
    0.08
    çļ®
    0.08
    ÑģеÑĤ
    0.08
    ecer
    0.08
    OI
    0.08
    Activations Density 0.193%

    No Known Activations