© 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. 50699
    Prev
    Next
    INDEX
    Explanations

    annual occurrences

    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
    idge
    -0.12
    ening
    -0.10
    æł·çļĦ
    -0.10
    ession
    -0.09
    ../../../
    -0.09
    elts
    -0.09
    lessness
    -0.09
    è¦ģ注æĦı
    -0.09
    etter
    -0.09
    folio
    -0.09
    POSITIVE LOGITS
    ized
    0.15
    ities
    0.13
    mente
    0.12
    ised
    0.12
    istic
    0.12
    itÃł
    0.12
    izing
    0.10
    ned
    0.10
    ugin
    0.10
    ity
    0.10
    Activations Density 0.023%

    No Known Activations