© 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. 36373
    Prev
    Next
    INDEX
    Explanations

    crawl, crawling, crawler, raw

    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
    TING
    -0.11
    ãĥ³ãĤ°
    -0.09
    çĦ¶æĺ¯
    -0.09
    inals
    -0.09
    ally
    -0.09
     УкÑĢа
    -0.09
    äºĭ
    -0.09
    amins
    -0.08
    fra
    -0.08
    ually
    -0.08
    POSITIVE LOGITS
    0.11
    iness
    0.10
    -mouth
    0.10
    shaw
    0.09
    é©¿
    0.09
    lords
    0.09
     decent
    0.09
    å¿ĥæĥ³
    0.09
    weise
    0.09
    ÑıÑī
    0.09
    Activations Density 0.009%

    No Known Activations