© 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. 1903
    Prev
    Next
    INDEX
    Explanations

    promises and pledges

    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
    è¤Ĵ
    -0.09
    åĬ³ç´¯
    -0.09
    欢ä¹IJ
    -0.09
    abee
    -0.09
    relude
    -0.08
    è£Ļ
    -0.08
    commons
    -0.08
    wel
    -0.08
    æĢĢçĸij
    -0.08
    åĶ
    -0.08
    POSITIVE LOGITS
    æī¿è¯º
    0.30
    èªĵè¨Ģ
    0.22
    èªĵ
    0.21
     promises
    0.21
     promise
    0.21
    Promise
    0.18
    promise
    0.18
     Promise
    0.18
    .Promise
    0.16
     vows
    0.16
    Activations Density 0.050%

    No Known Activations