© 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. 20325
    Prev
    Next
    INDEX
    Explanations

    job search and employment

    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§īéĨĴ
    -0.10
    å·¥ç¨ĭé¡¹çĽ®
    -0.09
    åĬ«
    -0.09
     обÑĭ
    -0.09
    icht
    -0.09
    ÃŃvel
    -0.09
     Outreach
    -0.08
    HEST
    -0.08
    åı¯è§Ĩ
    -0.08
    åıĹéĤĢ
    -0.08
    POSITIVE LOGITS
    å´ĸ
    0.09
    zar
    0.09
    athy
    0.09
    念
    0.08
    vant
    0.08
    anvas
    0.08
    ç¬Ļ
    0.08
    lix
    0.08
    çĶŁç´ł
    0.08
     Pier
    0.08
    Activations Density 0.033%

    No Known Activations