© 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. 52314
    Prev
    Next
    INDEX
    Explanations

    level of education or placement

    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
    æĿŁ
    -0.11
    æķĪ
    -0.10
    æªĢ
    -0.09
    å¸ĥ
    -0.09
    åĽ½æľī
    -0.09
    _trait
    -0.09
     nau
    -0.09
    åĴĮ个人
    -0.09
    æķ£åıij
    -0.08
     Armenia
    -0.08
    POSITIVE LOGITS
    å®īç½®
    0.10
     placement
    0.10
    æģ°å½ĵ
    0.09
    åħ¥åѦ
    0.09
    两级
    0.09
    placement
    0.08
    åĪĨæµģ
    0.08
    æ°ij
    0.08
     hitch
    0.08
    å±Ĥå±Ĥ
    0.08
    Activations Density 0.044%

    No Known Activations