© 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. 27004
    Prev
    Next
    INDEX
    Explanations

    state of being or becoming

    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
    utor
    -0.09
    orgh
    -0.09
    人éĥ½
    -0.08
    çļĦ人éĥ½
    -0.08
    åİ»äºĨ
    -0.08
     kì
    -0.08
    åħ¥åı£
    -0.08
     quyá»ģn
    -0.08
    jack
    -0.08
    ê¶Į
    -0.08
    POSITIVE LOGITS
     being
    0.23
    being
    0.20
     Being
    0.16
    Being
    0.16
     sendo
    0.16
     siendo
    0.13
     étant
    0.13
     needing
    0.12
     olması
    0.12
     becoming
    0.12
    Activations Density 0.161%

    No Known Activations