© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19795
    Prev
    Next
    INDEX
    Explanations

    men, officer, woman

    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
    çģĮ
    -0.09
    çĵ·
    -0.09
    æī¹éĩı
    -0.09
    rail
    -0.08
    (loader
    -0.08
    æĬķæĶ¾
    -0.08
    æİ¥è¿ij
    -0.08
    ÙĦاÙģ
    -0.08
    enville
    -0.08
    åĴ«
    -0.08
    POSITIVE LOGITS
    æ©Ľ
    0.10
     Sha
    0.09
    å®īä¿Ŀ
    0.08
    太åŃIJ
    0.08
    amu
    0.08
    çĻ¾ç§ij
    0.08
    å·¥ç¨ĭé¡¹çĽ®
    0.08
    åħ¬åħĥåīį
    0.08
    æŀģåħ¶
    0.08
    称ä¹ĭ
    0.08
    Activations Density 0.194%

    No Known Activations