© 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. 34692
    Prev
    Next
    INDEX
    Explanations

    credit card, loan, association

    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
    à¸Ľà¸£
    -0.09
     OWN
    -0.09
    azzi
    -0.09
    æ³¢çī¹
    -0.09
    å°İ
    -0.09
    fern
    -0.09
    ãĤ³ãĥŁ
    -0.09
    sWith
    -0.09
    chin
    -0.08
    åªĴä½ĵ
    -0.08
    POSITIVE LOGITS
    Jump
    0.09
    ëĬIJ
    0.09
    主æĦı
    0.09
    ÙģÙĪ
    0.09
    举åĮĹ
    0.08
    .Keyboard
    0.08
     powerhouse
    0.08
    缴è¨Ģ
    0.08
    èĭ±åĭĩ
    0.08
     enc
    0.08
    Activations Density 0.053%

    No Known Activations