© 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. 51877
    Prev
    Next
    INDEX
    Explanations

    Foundations and trusts

    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
    NM
    -0.10
     quo
    -0.10
    .jquery
    -0.09
    çĪ¬
    -0.09
    æĦŁ
    -0.09
    hon
    -0.09
    åĬ¿
    -0.09
    åѤåĦ¿
    -0.08
    空
    -0.08
    uber
    -0.08
    POSITIVE LOGITS
     اÙĦبÙĦ
    0.10
    otal
    0.10
    æĹĹä¸ĭçļĦ
    0.09
    èµĦåĬ©
    0.09
    ä¸įçķĻ
    0.09
    派驻
    0.09
    (KP
    0.09
    -funded
    0.09
    æĶ¯çº¿
    0.09
    éħįä¸Ĭ
    0.09
    Activations Density 0.015%

    No Known Activations