© 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. 3916
    Prev
    Next
    INDEX
    Explanations

    avoid

    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
    å°ı麦
    -0.09
    åĬłæ²¹
    -0.09
    olland
    -0.08
    ä¸įè¦ģåĨį
    -0.08
    acic
    -0.08
    uko
    -0.08
    Digest
    -0.08
    åĨ¤
    -0.08
    éļıæĦı
    -0.08
    æ¤Ĵ
    -0.08
    POSITIVE LOGITS
    æī¿æĭħ责任
    0.11
     Responsibility
    0.10
    oras
    0.10
    责任
    0.10
    æī¿æĭħ
    0.09
    neh
    0.09
     blame
    0.09
     responsibility
    0.09
    缮æłĩä»»åĬ¡
    0.09
     blames
    0.09
    Activations Density 0.022%

    No Known Activations