© 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. 36425
    Prev
    Next
    INDEX
    Explanations

    embroidered jewelry or art

    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
    ä½ľæĸĩ
    -0.10
    stub
    -0.09
    usal
    -0.08
    ult
    -0.08
    íĨł
    -0.08
    atives
    -0.08
    ê°Ħ
    -0.08
    æµģ转
    -0.08
    papers
    -0.08
    ponse
    -0.08
    POSITIVE LOGITS
    ein
    0.10
    ä¸ĢåľĪ
    0.10
    бил
    0.09
    -cols
    0.09
    tÃŃ
    0.09
    -spe
    0.09
    åı£å²¸
    0.09
    ifice
    0.08
    èĨº
    0.08
    asters
    0.08
    Activations Density 0.002%

    No Known Activations