© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35634
    Prev
    Next
    INDEX
    Explanations

    diploma or certificate

    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
    abouts
    -0.10
    lings
    -0.10
    ding
    -0.09
    wick
    -0.09
    æī£
    -0.09
    ç¦ıéŁ³
    -0.09
    ãĥĥãĤ°
    -0.09
    ãģĦãģĨ
    -0.09
    ellite
    -0.09
     mexico
    -0.09
    POSITIVE LOGITS
    matic
    0.11
    stry
    0.09
    azon
    0.09
    umba
    0.09
     повеÑĢ
    0.08
    æł·çļĦ
    0.08
    odal
    0.08
    IAS
    0.08
    é¦ĭ
    0.08
    wort
    0.08
    Activations Density 0.007%

    No Known Activations