© 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. 56120
    Prev
    Next
    INDEX
    Explanations

    food dishes and meal components

    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
    راء
    -0.08
    quarters
    -0.08
    sid
    -0.08
    .ua
    -0.08
     document
    -0.08
    chy
    -0.07
    åıįå¤į
    -0.07
    åĴĤ
    -0.07
     Ket
    -0.07
     habit
    -0.07
    POSITIVE LOGITS
    èµŀ
    0.11
    _EXECUTE
    0.10
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.10
    翱
    0.09
    åĽ¢
    0.09
    fant
    0.09
    为æĬĵ
    0.09
     اÙĦÙĪاØŃد
    0.09
    å·¡èĪª
    0.09
    çĤľ
    0.09
    Activations Density 0.003%

    No Known Activations