© 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. 17097
    Prev
    Next
    INDEX
    Explanations

    space after citation or legal document

    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
    åĦ¿
    -0.11
    满äºĨ
    -0.11
    zelf
    -0.10
    濯
    -0.09
    rupt
    -0.09
    åħĴ
    -0.09
    ì¡°
    -0.09
    burn
    -0.08
    ä¹ĥèĩ³
    -0.08
     Burn
    -0.08
    POSITIVE LOGITS
    efore
    0.09
    çĪ·
    0.09
    icher
    0.08
    UnderTest
    0.08
    ous
    0.08
    åľ°åĿª
    0.08
    _cube
    0.08
     flyer
    0.08
    amp
    0.08
    ries
    0.08
    Activations Density 0.093%

    No Known Activations