© 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. 52311
    Prev
    Next
    INDEX
    Explanations

    extracting

    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
    zilla
    -0.10
    nings
    -0.10
    liness
    -0.10
    acre
    -0.09
    boy
    -0.09
    alty
    -0.09
    atically
    -0.09
    boat
    -0.09
    ister
    -0.09
    uation
    -0.09
    POSITIVE LOGITS
    à¹Į
    0.12
    ively
    0.11
    ÑĢаÐ
    0.09
    rema
    0.09
    ivism
    0.09
    ordinary
    0.09
    OrUpdate
    0.09
     Aur
    0.08
    ters
    0.08
    زاد
    0.08
    Activations Density 0.045%

    No Known Activations