© 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. 30020
    Prev
    Next
    INDEX
    Explanations

    ellaStellaellenStellar

    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
    ening
    -0.10
    éĽ³
    -0.09
    vement
    -0.09
    TURE
    -0.09
    aters
    -0.09
    anas
    -0.09
    essler
    -0.09
    onom
    -0.09
    acity
    -0.09
    odox
    -0.08
    POSITIVE LOGITS
    ally
    0.10
    æģIJ
    0.09
    åŃĺåľ¨çļĦ
    0.09
    èĵį
    0.09
    reff
    0.09
    家éŨåı£
    0.09
    hani
    0.09
    主ä¹īèĢħ
    0.08
    ationship
    0.08
    ä½ľåĵģåĨħ容
    0.08
    Activations Density 0.012%

    No Known Activations