© 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. 36081
    Prev
    Next
    INDEX
    Explanations

    bottom line

    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
    ually
    -0.09
    eri
    -0.09
    orate
    -0.09
    ãģ¶
    -0.09
    -0.09
    uality
    -0.09
    ube
    -0.09
    顼
    -0.09
    lop
    -0.09
     недо
    -0.09
    POSITIVE LOGITS
    elig
    0.10
    -most
    0.10
    ties
    0.10
    ing
    0.10
    est
    0.09
    iez
    0.09
    ä»»ä½ķ人éĥ½
    0.09
    媳
    0.09
    tan
    0.09
    -tier
    0.09
    Activations Density 0.016%

    No Known Activations