© 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. 20419
    Prev
    Next
    INDEX
    Explanations

    website themes and scripts

    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
    ä¸Ģæľ¬
    -0.09
    anton
    -0.09
    ç²®é£Ł
    -0.08
    è¡ĢèĦī
    -0.08
    IDD
    -0.08
    fax
    -0.08
    vac
    -0.08
    ldr
    -0.08
    Interop
    -0.08
    çĽĺçĤ¹
    -0.08
    POSITIVE LOGITS
    è´¢åĬ¡ç®¡çIJĨ
    0.09
     Diy
    0.09
    踪
    0.09
    æĶ¿åĬ¡
    0.09
     blogger
    0.09
    æķĽ
    0.09
    ç¾¼
    0.09
     Blogger
    0.09
    .standard
    0.09
    agos
    0.09
    Activations Density 0.155%

    No Known Activations