© 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. 63475
    Prev
    Next
    INDEX
    Explanations

    theory, theories, and models

    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
     prio
    -0.09
    åĮĸè¿Ľç¨ĭ
    -0.08
     abstract
    -0.08
    ength
    -0.08
    åĩĨ
    -0.08
    æĹº
    -0.08
    妥
    -0.08
    Translations
    -0.07
    igin
    -0.07
    iron
    -0.07
    POSITIVE LOGITS
     theory
    0.21
    çIJĨ论
    0.20
    theory
    0.18
    Theory
    0.17
     Theory
    0.16
     theories
    0.15
    çIJĨè«ĸ
    0.15
     THEORY
    0.13
    模åŀĭ
    0.11
    åİŁçIJĨ
    0.11
    Activations Density 0.282%

    No Known Activations