© 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. 49546
    Prev
    Next
    INDEX
    Explanations

    medical therapy

    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
    åĺĺ
    -0.10
     Quiet
    -0.09
    éĹ»
    -0.08
    èĭ±éĽĦ
    -0.08
    æĢľ
    -0.08
    ä¾£
    -0.08
    ç´ł
    -0.08
    çļĦç¾İ好
    -0.08
    ilo
    -0.08
    é²ł
    -0.08
    POSITIVE LOGITS
    è¾ħ
    0.10
    è¿Ļä¹Ī说
    0.09
    ings
    0.09
    Ùħد
    0.09
     disp
    0.09
    Hat
    0.09
    诫
    0.09
    apore
    0.09
    tings
    0.09
    éĻįèIJ½
    0.08
    Activations Density 0.027%

    No Known Activations