© 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. 37659
    Prev
    Next
    INDEX
    Explanations

    purchase tickets in advance

    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
    å½ĵå±Ģ
    -0.09
    æįŀ
    -0.09
    èģĶåIJĪ
    -0.09
    失踪
    -0.08
    cura
    -0.08
    çĺ¾
    -0.08
    olics
    -0.08
    èµĽåIJİ
    -0.08
    å°ıéķĩ
    -0.08
    æĬī
    -0.08
    POSITIVE LOGITS
    åı
    0.10
    æĹ©
    0.10
    shal
    0.09
    å°½æĹ©
    0.09
    OOM
    0.09
    TERM
    0.09
    ium
    0.09
    omatic
    0.08
    é¢ĦåĶ®
    0.08
    ordial
    0.08
    Activations Density 0.005%

    No Known Activations