© 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. 27635
    Prev
    Next
    INDEX
    Explanations

    pension related terms

    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
    fulness
    -0.11
    ness
    -0.11
    ÑĩаÑĤ
    -0.11
    æĦŁæŁĵ
    -0.10
     ÑģовеÑĢÑĪен
    -0.09
    æ°Ķæ°Ľ
    -0.09
    -signed
    -0.09
    ulp
    -0.09
    åIJįå¸Ī
    -0.09
     reve
    -0.09
    POSITIVE LOGITS
    umer
    0.11
    etwork
    0.10
    ary
    0.10
    edly
    0.09
    naire
    0.09
    eer
    0.09
    ifer
    0.09
    als
    0.09
    ÑĢÑĥж
    0.09
    naires
    0.09
    Activations Density 0.010%

    No Known Activations