© 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. 62528
    Prev
    Next
    INDEX
    Explanations

    benefit, beneficiary, or benefited

    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
    åī§ç»Ħ
    -0.10
    èĴŁ
    -0.10
    åĮ¾
    -0.10
    flix
    -0.09
    ç¢Ł
    -0.09
    xBB
    -0.09
    ForResource
    -0.09
    ãĤ
    -0.09
    åı¯æĢķçļĦ
    -0.09
    ople
    -0.09
    POSITIVE LOGITS
    åıĹçĽĬ
    0.15
    å¾ĹçĽĬ
    0.12
     beneficiary
    0.10
     benefit
    0.10
    à¸Īาà¸ģà¸ģาร
    0.09
     beneficiaries
    0.09
     Benef
    0.09
    arten
    0.09
    benef
    0.09
    avored
    0.09
    Activations Density 0.034%

    No Known Activations