© 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. 6762
    Prev
    Next
    INDEX
    Explanations

    not supported or receive

    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
    æŶåĪ»
    -0.10
    æľīä¸įåIJĮçļĦ
    -0.10
    åĬĽæ±Ĥ
    -0.09
     AUTHORS
    -0.09
    妣
    -0.09
    è¿Ļå°±æĺ¯
    -0.08
    _nullable
    -0.08
    pond
    -0.08
    aven
    -0.08
    å¿ĥæĥ³
    -0.08
    POSITIVE LOGITS
    çīŁ
    0.10
    sw
    0.09
    swire
    0.08
    بÙĦ
    0.08
    åħī彩
    0.08
    亲身
    0.08
    icias
    0.08
    ç©¿è¡£
    0.08
    kie
    0.08
    theless
    0.08
    Activations Density 0.115%

    No Known Activations