© 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. 18047
    Prev
    Next
    INDEX
    Explanations

    ordinals and numbers

    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
     merit
    -0.08
    åıĮèħ¿
    -0.08
    urge
    -0.08
    OrCreate
    -0.08
    dance
    -0.08
    unte
    -0.08
    Mit
    -0.08
    å¤ļå¹´åīį
    -0.08
    izza
    -0.08
    æĮĩæĮ¥
    -0.08
    POSITIVE LOGITS
    ĸ
    0.11
    elas
    0.11
    åĢĮ
    0.10
    èĭ¥å¹²
    0.10
    neck
    0.10
    ä¸Ńå¤ĸ
    0.09
    ä¸ĢèĦļ
    0.09
    sole
    0.09
    -dess
    0.09
    bine
    0.09
    Activations Density 0.088%

    No Known Activations