© 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. 5257
    Prev
    Next
    INDEX
    Explanations

    reporting to superiors or bosses

    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
    纤
    -0.09
    çĪ¶åŃIJ
    -0.09
    å±İ
    -0.09
    isch
    -0.09
    åĪĨè¡Į
    -0.08
    наÑĤ
    -0.08
    æĪ¡
    -0.08
    ä¸Ŀä¸Ŀ
    -0.08
    åīį线
    -0.08
    湫
    -0.08
    POSITIVE LOGITS
    ä¸Ĭ级
    0.11
    ä¸įçĶ±
    0.09
    ä¸Ĭåı¸
    0.09
     boss
    0.09
    Boss
    0.09
     Ùħباشرة
    0.09
    è°İ
    0.09
    boss
    0.09
     Boss
    0.09
    .histogram
    0.09
    Activations Density 0.040%

    No Known Activations