© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8057
    Prev
    Next
    INDEX
    Explanations

    job searches and employment qualifications

    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
    好å¥ĩå¿ĥ
    -0.10
    为äºĨ让
    -0.10
    å·®çĤ¹
    -0.09
    代è¨Ģ人
    -0.09
    çĪ±ç¾İ
    -0.09
    åŃĢ
    -0.09
    å¸ĪèµĦ
    -0.09
    å¾Ĺ天çĭ¬åİļ
    -0.08
    红æĺŁ
    -0.08
    个åĪ«
    -0.08
    POSITIVE LOGITS
     NRA
    0.10
    IRA
    0.10
    ä¸Ģå¤ľ
    0.09
    温
    0.08
     TNT
    0.08
    hydr
    0.08
    ÑīÑĥ
    0.08
    outers
    0.08
    ابÙĦ
    0.08
    antom
    0.08
    Activations Density 0.103%

    No Known Activations