© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35543
    Prev
    Next
    INDEX
    Explanations

    expect/ask/suppose/hope

    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
    åİĭåĬĽ
    -0.09
    åIJİåı°
    -0.09
    иÑģк
    -0.08
    好åĩłä¸ª
    -0.08
    ä¸įåı¯
    -0.08
    èĩ³å°ij
    -0.08
    æĦıåIJij
    -0.08
    gor
    -0.08
    urg
    -0.08
     Rays
    -0.08
    POSITIVE LOGITS
    æĢİä¹Īåı¯èĥ½
    0.10
    禳
    0.10
    èĬ±æľµ
    0.10
    ä¹Łä¸įåı¯èĥ½
    0.10
    asket
    0.10
    çĪ±ä¸Ĭ
    0.10
    责令
    0.09
    è¿Ķè¿ĺ
    0.09
    IBE
    0.09
    è¡
    0.09
    Activations Density 0.028%

    No Known Activations