© 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. 33948
    Prev
    Next
    INDEX
    Explanations

    school meals for children

    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
    ibase
    -0.12
    rote
    -0.10
    足
    -0.10
    ç«
    -0.09
    èĻ±
    -0.09
    奴
    -0.09
    bish
    -0.08
     geg
    -0.08
     máºŃt
    -0.08
    çīµ
    -0.08
    POSITIVE LOGITS
    .pp
    0.09
    带头
    0.09
    èµ·çłģ
    0.09
    bery
    0.09
    çĶŁåij½åĬĽ
    0.09
    殿åłĤ
    0.09
    奶
    0.09
    ç»ĻæĪij们
    0.09
    pread
    0.09
    ulti
    0.09
    Activations Density 0.084%

    No Known Activations