© 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. 55991
    Prev
    Next
    INDEX
    Explanations

    tribute paid to

    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
    ago
    -0.11
    itz
    -0.11
    ities
    -0.10
    ague
    -0.10
    overs
    -0.09
    erva
    -0.09
    æŃ¤é¡¹
    -0.09
    ales
    -0.09
    s
    -0.09
    触åĬ¨
    -0.09
    POSITIVE LOGITS
    глав
    0.10
    semb
    0.10
    IVAL
    0.10
    ductory
    0.09
    ÑĢод
    0.09
    .Undef
    0.09
    anden
    0.09
    -Mart
    0.09
    åĵģ
    0.09
    odal
    0.09
    Activations Density 0.004%

    No Known Activations