© 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. 39307
    Prev
    Next
    INDEX
    Explanations

    et cetera, et al, etymology

    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
    nable
    -0.10
    ye
    -0.09
    ous
    -0.09
     дÑĥÑħ
    -0.09
    çķ¿
    -0.09
    éľĨ
    -0.08
    clar
    -0.08
    zilla
    -0.08
    uez
    -0.08
    atica
    -0.08
    POSITIVE LOGITS
    TING
    0.13
    ymology
    0.12
    ters
    0.12
    ched
    0.11
    ernal
    0.11
    ting
    0.11
    tings
    0.11
    udiant
    0.11
    ablish
    0.10
    ienne
    0.10
    Activations Density 0.038%

    No Known Activations