© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63766
    Prev
    Next
    INDEX
    Explanations

    promise and fulfillment

    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
    åıįæĺłåĩº
    -0.09
    ensis
    -0.09
    æµģ失
    -0.09
    ä¸Ģä¸ĭåŃIJå°±
    -0.09
    ìĽIJ
    -0.09
    à¹Ħล
    -0.08
    è·Į
    -0.08
    uien
    -0.08
    ASM
    -0.08
     ÑģовеÑĢÑĪ
    -0.08
    POSITIVE LOGITS
    åħijçİ°
    0.21
    æī¿è¯º
    0.20
     promised
    0.16
     promise
    0.16
     promises
    0.15
     Promise
    0.14
    Promise
    0.13
    è·µ
    0.13
    promise
    0.13
    约å®ļ
    0.12
    Activations Density 0.049%

    No Known Activations