© 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. 3874
    Prev
    Next
    INDEX
    Explanations

    spouse or partner

    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
    å¾Ĺ太
    -0.11
    ulous
    -0.11
    å¿«æĬ¥
    -0.10
    ãģıãĤĮ
    -0.09
    IBE
    -0.09
    åĪ°è¿ĻéĩĮ
    -0.09
    arios
    -0.09
    UMB
    -0.09
    oted
    -0.09
    isex
    -0.09
    POSITIVE LOGITS
    LESS
    0.10
    less
    0.10
    éĹ´çļĦ
    0.10
    åIJİèĢħ
    0.09
    çĶ¨åĵģ
    0.09
    ê°Ħ
    0.09
    åīįèĢħ
    0.09
    hood
    0.08
    able
    0.08
     Newport
    0.08
    Activations Density 0.013%

    No Known Activations