© 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. 51996
    Prev
    Next
    INDEX
    Explanations

    memorable stories, impressions, travel, moments

    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
    amba
    -0.11
    å·§
    -0.10
    女æİĴ
    -0.08
    æµģè¡ĮçļĦ
    -0.08
    bung
    -0.08
     gar
    -0.08
    ech
    -0.08
    èĩ¾
    -0.08
    .pb
    -0.08
    /module
    -0.08
    POSITIVE LOGITS
    .Restrict
    0.10
     Ott
    0.10
    ç»į
    0.09
    æīĢåľ¨
    0.09
    峡
    0.09
     Bain
    0.09
     Ñĥни
    0.09
    èµī
    0.09
    OLT
    0.09
    次ä¼ļè®®
    0.09
    Activations Density 0.005%

    No Known Activations