© 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. 20441
    Prev
    Next
    INDEX
    Explanations

    hello world

    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
    amp
    -0.10
    uele
    -0.09
    ì¹ĺ
    -0.09
    race
    -0.08
    loth
    -0.08
    ball
    -0.08
     enlarge
    -0.08
     allen
    -0.08
    lets
    -0.08
    елÑı
    -0.08
    POSITIVE LOGITS
    ance
    0.11
    brew
    0.09
    /or
    0.09
    oooo
    0.09
    åĢĮ
    0.09
    èĭ£
    0.09
    模èĮĥ
    0.09
    æ¹ľ
    0.09
    åįķä»·
    0.08
    缨
    0.08
    Activations Density 0.022%

    No Known Activations