© 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. 4849
    Prev
    Next
    INDEX
    Explanations

    syphilis, gonorrhea, disease

    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
    azz
    -0.10
    æ´¾
    -0.09
    æ±
    -0.09
    tor
    -0.09
    .annot
    -0.09
    .party
    -0.09
    è¡Ļ
    -0.08
    éŃĦ
    -0.08
    屿
    -0.08
    åİ®
    -0.08
    POSITIVE LOGITS
    emen
    0.10
    渣
    0.08
    æĬµ
    0.08
    ened
    0.08
    endants
    0.08
    _INLINE
    0.08
    Inside
    0.08
    çŀ½
    0.08
     condu
    0.08
    bet
    0.08
    Activations Density 0.004%

    No Known Activations