© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20795
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
    éħį
    -0.11
    rais
    -0.09
    locker
    -0.08
    çĶŁäº§æĢ»
    -0.08
    æĦŁæĤŁ
    -0.08
    omic
    -0.08
    hab
    -0.08
    ipy
    -0.08
    inspace
    -0.08
    stack
    -0.08
    POSITIVE LOGITS
    è´Łè´£
    0.09
    ç¬ĥ
    0.09
    è²łè²¬
    0.09
    éĶ¥
    0.08
    è¾¾
    0.08
    åķĨè´¸
    0.08
    åĩłå®¶
    0.08
    mons
    0.08
    åı¯ä»¥å¸®åĬ©
    0.08
    iles
    0.08
    Activations Density 0.039%

    No Known Activations