© 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. 38703
    Prev
    Next
    INDEX
    Explanations

    credit score enquiries

    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¸įå¼Ģ
    -0.10
    翦
    -0.09
    èIJ±
    -0.09
    车éĺŁ
    -0.09
    éħ£
    -0.08
    åĴ«
    -0.08
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.08
    relation
    -0.08
    çļĦ表æĥħ
    -0.08
     ey
    -0.08
    POSITIVE LOGITS
    å¾ģä¿¡
    0.14
    ä¿¡çĶ¨
    0.12
    éĵĨ
    0.10
     credit
    0.09
    inos
    0.09
    -score
    0.09
    å±ıå¹ķä¸Ĭ
    0.09
    éĩijèŀįå¸Ĥåľº
    0.09
    äººæł¼
    0.08
     accessed
    0.08
    Activations Density 0.037%

    No Known Activations