© 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. 1821
    Prev
    Next
    INDEX
    Explanations

    full-time employment or unemployment

    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
     Unlock
    -0.10
    -dollar
    -0.09
    绽
    -0.09
    大èĥĨ
    -0.09
    enor
    -0.09
    çł´ç¢İ
    -0.09
    ÑħоÑĤ
    -0.09
    åķ¬
    -0.08
    å°ıçĶ·åŃ©
    -0.08
    ddie
    -0.08
    POSITIVE LOGITS
    失ä¸ļ
    0.17
     unemployment
    0.17
     unemployed
    0.16
    å°±ä¸ļ
    0.14
    ä¸ĵèģĮ
    0.13
    åħ¨æĹ¥åĪ¶
    0.11
     employment
    0.11
    æ±ĤèģĮ
    0.10
    èģ·
    0.10
     Employment
    0.10
    Activations Density 0.146%

    No Known Activations