© 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. 5719
    Prev
    Next
    INDEX
    Explanations

    real estate investment properties

    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
    è¹Ī
    -0.11
    æīĵåħ¥
    -0.10
    移åĬ¨ç«¯
    -0.10
    é¹Ħ
    -0.10
    让æ¶Īè´¹èĢħ
    -0.10
    è®´
    -0.10
    åħ¥åѦ
    -0.10
    èµ°å¾Ĺ
    -0.10
    导åħ¥
    -0.10
    åĴİ
    -0.10
    POSITIVE LOGITS
    åĩºç§Ł
    0.11
    æĶ¶è´Ń
    0.09
    gly
    0.08
    oci
    0.08
    ä¸įåģľ
    0.08
    ç¢
    0.08
    ocol
    0.08
    笳
    0.07
    宿
    0.07
    æĵĴ
    0.07
    Activations Density 0.125%

    No Known Activations