© 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. 55828
    Prev
    Next
    INDEX
    Explanations

    grief and bereavement

    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
    aneous
    -0.09
    ç¿ķ
    -0.09
    phan
    -0.09
    å¿ĥæĦı
    -0.09
    çľĭ好
    -0.08
    ities
    -0.08
    arter
    -0.08
    å¾ģæĶ¶
    -0.08
    èĦį
    -0.08
    ized
    -0.08
    POSITIVE LOGITS
    fully
    0.12
    ening
    0.11
    ipel
    0.10
    漪
    0.10
    çĭ¬è§Ĵ
    0.10
    ened
    0.09
    伤å¿ĥ
    0.09
    ä¹ĭä½Ļ
    0.09
    -quarters
    0.09
    yards
    0.09
    Activations Density 0.007%

    No Known Activations