© 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. 1428
    Prev
    Next
    INDEX
    Explanations

    cutting tools and equipment

    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
     ngu
    -0.09
    arius
    -0.09
     paralysis
    -0.09
     Alam
    -0.08
    é£ŁæĿIJ
    -0.08
    lio
    -0.08
    æĬµå¾¡
    -0.08
    ograms
    -0.08
    åŀĽ
    -0.08
    DEX
    -0.08
    POSITIVE LOGITS
    åīª
    0.11
     scissors
    0.11
    çłį
    0.11
    åĪĩåī²
    0.11
    åĩ¿
    0.11
    Õ³
    0.10
    çIJ¢
    0.10
    åīĬ
    0.10
    xes
    0.10
    issors
    0.10
    Activations Density 0.079%

    No Known Activations