© 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. 30120
    Prev
    Next
    INDEX
    Explanations

    divorce and separation

    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
    妥åĸĦ
    -0.10
    æ°ijä¼ģ
    -0.09
    è°Ĭ
    -0.09
    æ¯ĸ
    -0.09
    绢
    -0.09
    çłĴ
    -0.09
     reb
    -0.09
    por
    -0.09
    éħ£
    -0.09
    ((__
    -0.09
    POSITIVE LOGITS
    oce
    0.09
    å·²ä¹ħ
    0.08
     Parad
    0.08
    ement
    0.08
    伫
    0.08
    nish
    0.08
    ayed
    0.08
    åħ·ä½ĵåĨħ容
    0.08
    é»ĺé»ĺ
    0.08
    åѤ
    0.08
    Activations Density 0.015%

    No Known Activations