© 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. 27265
    Prev
    Next
    INDEX
    Explanations

    mobility and student loans

    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
    å¸IJ
    -0.09
    åĨħ马
    -0.08
    çŃ¹
    -0.08
    åİ¢
    -0.08
     Arn
    -0.08
    éĻĦ
    -0.08
    æijĺ
    -0.08
    illard
    -0.08
    çŃĴ
    -0.08
     excess
    -0.08
    POSITIVE LOGITS
    åĩıåħį
    0.12
    apol
    0.10
    apo
    0.10
    失ä¸ļ
    0.10
    æĹłåĬ©
    0.10
    unan
    0.10
    çľ¼è§Ĵ
    0.09
    äºĭåħ³
    0.09
    æ²IJæµ´
    0.09
    åĴĮ社ä¼ļ
    0.09
    Activations Density 0.075%

    No Known Activations