© 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. 33571
    Prev
    Next
    INDEX
    Explanations

    acrylic and its compounds

    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
    .itemView
    -0.11
    éļħ
    -0.11
    .chomp
    -0.10
    pec
    -0.10
    MUX
    -0.10
    ioso
    -0.10
    rys
    -0.10
    ราà¸Ĭà¸ģาร
    -0.10
    åĴĮåľ°åĮº
    -0.09
    ertz
    -0.09
    POSITIVE LOGITS
    ../../../
    0.11
    top
    0.09
    t
    0.09
    ucas
    0.09
    0.09
    ä¸ĩæĪ·
    0.09
    signature
    0.08
    æĿ·
    0.08
    ITY
    0.08
    vas
    0.08
    Activations Density 0.018%

    No Known Activations