© 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. 56646
    Prev
    Next
    INDEX
    Explanations

    death and medical events

    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
    è¹Ħ
    -0.09
    è¯İ
    -0.09
    urr
    -0.09
    åĿļå®ļ
    -0.09
    æݳ
    -0.09
    åĽļ
    -0.09
    arity
    -0.09
    åѵ
    -0.08
    ç¾½æ¯Ľ
    -0.08
    çī§åľº
    -0.08
    POSITIVE LOGITS
    çĶŁåij½
    0.10
    å¥Ħ
    0.10
    çĶŁåij½çļĦ
    0.10
    æĬ¢æķij
    0.09
    æį¡
    0.09
    ä¸įä¹ħ
    0.09
    _VENDOR
    0.08
    çļĦçĶŁåij½
    0.08
    æIJı
    0.08
    å½ĵåľº
    0.08
    Activations Density 0.067%

    No Known Activations