© 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. 23314
    Prev
    Next
    INDEX
    Explanations

    scrapped, target, demolition, raised, uncovered

    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
    loyd
    -0.09
    éļĶ
    -0.08
    ucchini
    -0.08
     plagiar
    -0.08
    .species
    -0.08
    جÙĬ
    -0.08
    æī¿æĭħ
    -0.08
    ÙĤÙĦ
    -0.08
    ÙĨشأ
    -0.08
    çĿļ
    -0.08
    POSITIVE LOGITS
    æĭĨ
    0.11
    å®Į好
    0.11
    鼶éĥ¨ä»¶
    0.11
    éĢĢå½¹
    0.11
    åłĨ
    0.10
    æĬ¥åºŁ
    0.10
    å°½åı¯èĥ½
    0.09
    åIJĬ
    0.09
     Pieces
    0.09
     dest
    0.09
    Activations Density 0.104%

    No Known Activations