© 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. 36380
    Prev
    Next
    INDEX
    Explanations

    eternal, timeless, immortal, everlasting

    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
     clearing
    -0.09
    çĽij
    -0.09
    Leod
    -0.08
    庵
    -0.08
     Chand
    -0.08
     luk
    -0.08
    åѤ
    -0.08
     Ao
    -0.08
    Ñģл
    -0.08
    -slide
    -0.08
    POSITIVE LOGITS
    æ°¸æģĴ
    0.20
    æ°¸
    0.18
    æ°¸è¿ľä¸įä¼ļ
    0.16
     timeless
    0.15
    æ°¸ä¹ħ
    0.15
     eternal
    0.14
     Eternal
    0.14
    æĮģä¹ħ
    0.13
    æ°¸è¿ľ
    0.13
     everlasting
    0.13
    Activations Density 0.045%

    No Known Activations