© 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. 58994
    Prev
    Next
    INDEX
    Explanations

    some } X

    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
    翳
    -0.09
     Rum
    -0.09
    è¿Ļç§įæĥħåĨµ
    -0.08
     little
    -0.08
    åį¡çīĩ
    -0.08
     somewhat
    -0.08
    å°½åĬĽ
    -0.08
     poco
    -0.08
    little
    -0.08
    äº
    -0.07
    POSITIVE LOGITS
    cpy
    0.09
     пÑģиÑħолог
    0.08
    èŤ
    0.08
    å¤¸å¼ł
    0.08
    ivr
    0.08
    kol
    0.08
    anic
    0.08
    ENO
    0.08
    apter
    0.08
    earn
    0.08
    Activations Density 0.058%

    No Known Activations