© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1379
    Prev
    Next
    INDEX
    Explanations

    leon names and suffixes

    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
    ties
    -0.11
    ente
    -0.10
    éħª
    -0.10
     liá»ĩu
    -0.09
    èĥĽ
    -0.09
    entes
    -0.09
    weed
    -0.08
    sWith
    -0.08
    wahl
    -0.08
    åĴĮåľ°åĮº
    -0.08
    POSITIVE LOGITS
    ffer
    0.10
    ards
    0.10
    é¢ı
    0.10
    idas
    0.10
    æĻ°
    0.10
    ally
    0.09
    strate
    0.09
    ÑĥÑĪки
    0.09
    ide
    0.09
    ä¹İ
    0.09
    Activations Density 0.018%

    No Known Activations