© 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. 18959
    Prev
    Next
    INDEX
    Explanations

    where to buy or get

    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
    ewn
    -0.09
    ú
    -0.09
     sod
    -0.08
    大ä¼ļ
    -0.08
    son
    -0.08
    è¿ijè§Ĩ
    -0.08
    æĪİ
    -0.08
    sock
    -0.08
    åĪ°äºĨ
    -0.08
    é¦Ĩ
    -0.08
    POSITIVE LOGITS
    ä½ķå¤Ħ
    0.13
    ä¸Ģç«Ļ
    0.13
    讳
    0.10
    ä»Ģä¹Īåľ°æĸ¹
    0.10
    clause
    0.09
    è§ħ
    0.09
    æłĸ
    0.09
    heimer
    0.09
    /us
    0.09
    åIJĪéĢĤçļĦ
    0.09
    Activations Density 0.027%

    No Known Activations