© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8691
    Prev
    Next
    INDEX
    Explanations

    taste buds

    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
    ity
    -0.10
    ders
    -0.10
    rd
    -0.09
    tera
    -0.09
    med
    -0.09
    atically
    -0.09
    ester
    -0.09
    istrator
    -0.09
    itaire
    -0.09
    ERIC
    -0.09
    POSITIVE LOGITS
    less
    0.15
    LESS
    0.14
    lessness
    0.13
    åĻĮ
    0.13
    ably
    0.12
    heet
    0.12
    heets
    0.12
    ings
    0.11
    ABLE
    0.11
    ful
    0.11
    Activations Density 0.007%

    No Known Activations