© 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. 4721
    Prev
    Next
    INDEX
    Explanations

    anywhere or any kind

    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
    edList
    -0.09
    Susp
    -0.09
    以èī²
    -0.09
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.08
    listing
    -0.08
    é¦Ķ
    -0.08
    æĸ¹æīį
    -0.08
    AFE
    -0.08
    lower
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ
    0.20
     лÑİбого
    0.18
     лÑİбой
    0.17
    åıªè¦ģæĺ¯
    0.16
    åıªè¦ģæľī
    0.16
    ä»»ä½ķä¸Ģ个
    0.16
    ä»»ä½ķ人
    0.16
    åıªè¦ģä½ł
    0.14
     any
    0.14
     qualquer
    0.14
    Activations Density 0.114%

    No Known Activations