© 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. 49525
    Prev
    Next
    INDEX
    Explanations

    insurance premiums and costs

    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
    rain
    -0.08
    æ·Į
    -0.08
    ç»ıæµİ
    -0.08
    éĦ¯
    -0.08
     economic
    -0.08
    icolor
    -0.07
     posts
    -0.07
    ront
    -0.07
    ern
    -0.07
    è°
    -0.07
    POSITIVE LOGITS
    ä¿Ŀè´¹
    0.12
    éķ¿å¤§
    0.10
    çŀĴ
    0.10
    STALL
    0.10
     wysoko
    0.10
    зи
    0.09
    otime
    0.09
     premiums
    0.09
     поÑģл
    0.09
    licensed
    0.09
    Activations Density 0.030%

    No Known Activations