© 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. 22037
    Prev
    Next
    INDEX
    Explanations

    great followed by specific nouns

    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
    ither
    -0.08
    ç«ĭ足
    -0.08
    arring
    -0.08
    满æĢĢ
    -0.08
    ecal
    -0.08
     prim
    -0.08
     prov
    -0.08
    ulin
    -0.08
    eled
    -0.08
    -sided
    -0.08
    POSITIVE LOGITS
    ness
    0.17
    ington
    0.13
    ly
    0.12
    INGTON
    0.11
    omy
    0.11
    mente
    0.11
    ertas
    0.10
    ths
    0.10
    erness
    0.10
    ened
    0.09
    Activations Density 0.017%

    No Known Activations