© 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. 31954
    Prev
    Next
    INDEX
    Explanations

    youth team career

    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
    éº»æľ¨
    -0.10
    缸åħ³åĨħ容
    -0.10
    èĪĤ
    -0.09
     Mash
    -0.09
     Cooke
    -0.09
    åIJįåĪĹ
    -0.09
    éĢıæĺİ
    -0.08
    errs
    -0.08
    ä¸Ģ家
    -0.08
    å±
    -0.08
    POSITIVE LOGITS
     Bik
    0.09
    ãģĦãģĭ
    0.08
     agitation
    0.08
    crow
    0.08
    Corp
    0.08
    uteur
    0.08
    .bl
    0.08
    åłĥ
    0.08
    åĩĨ
    0.08
    贯彻èIJ½å®ŀ
    0.08
    Activations Density 0.174%

    No Known Activations