© 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. 27714
    Prev
    Next
    INDEX
    Explanations

    women, empowerment, community organizations

    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
    è°ĪæģĭçĪ±
    -0.09
    ikk
    -0.08
     Gaines
    -0.08
    edm
    -0.08
     aure
    -0.08
    è¡Įäºĭ
    -0.08
    _ptrs
    -0.08
     Bowl
    -0.08
     EDM
    -0.08
    åħ¬åħ³
    -0.08
    POSITIVE LOGITS
    å°ıé¢Ŀ
    0.12
    å°ıé¢Ŀ贷款
    0.11
    å¦ĩ女
    0.11
    大å§IJ
    0.10
    æĿijæ°ij
    0.10
    æī¶è´«
    0.10
    樵
    0.10
    ç¼ĸç»ĩ
    0.10
     chá»ĭ
    0.09
    éĺ¿å§¨
    0.09
    Activations Density 0.090%

    No Known Activations