© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19988
    Prev
    Next
    INDEX
    Explanations

    lifetime

    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
    åĩ»
    -0.10
    åijĨ
    -0.09
    åıªæĥ³
    -0.09
    à¸Ĺะ
    -0.09
    ovan
    -0.08
     TAR
    -0.08
     gó
    -0.08
    productive
    -0.08
    ÙĦØ©
    -0.08
    ipt
    -0.08
    POSITIVE LOGITS
    ä¸Ģ代
    0.16
    äº²çľ¼
    0.15
     lifetime
    0.14
    æĹ¶ä»£çļĦ
    0.13
    ä¸ī代
    0.13
    ä¸ĢçĶŁ
    0.13
    æľŁåĨħ
    0.13
    lifetime
    0.12
    ä¸ĸ代
    0.12
     Lifetime
    0.12
    Activations Density 0.071%

    No Known Activations