© 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. 4557
    Prev
    Next
    INDEX
    Explanations

    cuts spending, costs, or rates

    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
    ä¸Ńåħ³
    -0.10
    åİĤæĪ¿
    -0.09
     inev
    -0.09
    ajs
    -0.09
    shore
    -0.09
    èĻı
    -0.08
    çĶ¢æ¥Ń
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
     вал
    -0.08
    ecess
    -0.08
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.12
    å°¾
    0.11
    çī
    0.10
     voting
    0.09
    leg
    0.08
    ãģ»ãģ¨
    0.08
    åĪ°æľĢåIJİ
    0.08
    尾巴
    0.08
     rum
    0.08
    æļĸæ°Ķ
    0.08
    Activations Density 0.013%

    No Known Activations