© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7769
    Prev
    Next
    INDEX
    Explanations

    assurance and confidence

    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
    untu
    -0.09
    itures
    -0.09
    zilla
    -0.09
    è¿Ľåĩº
    -0.09
    ucid
    -0.08
    åīįä¸ī
    -0.08
    Translated
    -0.08
     поÑĤеÑĢ
    -0.08
    ä»ĸèĩªå·±
    -0.08
    ä¸ŃåİŁ
    -0.08
    POSITIVE LOGITS
    ars
    0.09
    æ°´åĩĨ
    0.09
    ARP
    0.08
    رت
    0.08
    æ±Łä¸ľ
    0.08
    åĵģè´¨
    0.08
    çĽ²
    0.08
     ë¨
    0.08
    vis
    0.08
    æ³±
    0.08
    Activations Density 0.031%

    No Known Activations