© 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. 21029
    Prev
    Next
    INDEX
    Explanations

    wire communication

    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
    æĬ¤èº«
    -0.10
    ä¸ĢæĿ¡é¾Ļ
    -0.09
    èį¯ä¸ļ
    -0.09
    rais
    -0.08
    æĬľ
    -0.08
    ened
    -0.08
    ä¸ĬéŨ
    -0.08
    rees
    -0.08
    shi
    -0.08
    _rights
    -0.08
    POSITIVE LOGITS
    lessly
    0.10
    ãĥ¼ãĥī
    0.09
    ILI
    0.09
    ikip
    0.09
    俶
    0.09
    backs
    0.09
    locator
    0.09
     пÑĢид
    0.09
    vious
    0.09
    alm
    0.09
    Activations Density 0.014%

    No Known Activations