© 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. 5181
    Prev
    Next
    INDEX
    Explanations

    packaging and wrapping

    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
    修补
    -0.10
    æīĢå¾Ĺ
    -0.10
    è¤Ĥ
    -0.09
     ведÑĮ
    -0.09
     Dover
    -0.08
    寶
    -0.08
    头çļ®
    -0.08
    Sdk
    -0.08
    ä¸Ģ头
    -0.08
    èį·
    -0.08
    POSITIVE LOGITS
    åĮħè£ħ
    0.24
     packaging
    0.18
     Packaging
    0.16
    å°ģè£ħ
    0.12
     wrapping
    0.12
    .unwrap
    0.11
     wrapper
    0.11
    wrap
    0.11
    è£ħ
    0.11
     envelop
    0.11
    Activations Density 0.109%

    No Known Activations