© 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. 49154
    Prev
    Next
    INDEX
    Explanations

    work and life balance

    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
    plib
    -0.09
    Serializable
    -0.09
    æĩĴ
    -0.08
    æĢł
    -0.08
    寡
    -0.08
    ense
    -0.08
    è´²
    -0.08
    强迫
    -0.08
    eks
    -0.08
    æºĥ
    -0.08
    POSITIVE LOGITS
    èĤ²åĦ¿
    0.13
    åħ¼é¡¾
    0.12
    家åĬ¡
    0.11
    åĵºä¹³
    0.11
    å©´å¹¼åĦ¿
    0.10
    åħ»èĤ²
    0.10
     childcare
    0.10
    çħ§é¡¾
    0.10
    å©´åĦ¿
    0.10
    çļĦå·¥ä½ľ
    0.09
    Activations Density 0.240%

    No Known Activations