© 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. 56864
    Prev
    Next
    INDEX
    Explanations

    training and education

    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
    asca
    -0.10
    é«ĵ
    -0.10
    æľīæĿ¡ä»¶
    -0.09
    åıĹ欢è¿İ
    -0.09
    æĹ¥æĬ¥ç¤¾
    -0.09
    rut
    -0.09
    çĤ¹å¤ļ
    -0.08
    urm
    -0.08
    ä¸Ģç«Ļ
    -0.08
    åĩºåĵģ
    -0.08
    POSITIVE LOGITS
    åŁ¹è®Ń
    0.27
     training
    0.22
    è®Ńç»ĥ
    0.19
     trained
    0.18
    training
    0.17
     Training
    0.17
    æķĻèĤ²åŁ¹è®Ń
    0.17
    -training
    0.17
    .training
    0.16
    Training
    0.16
    Activations Density 0.098%

    No Known Activations