© 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. 10114
    Prev
    Next
    INDEX
    Explanations

    be sure to

    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
    alf
    -0.09
    Purple
    -0.09
    ä»ĺ
    -0.09
     civ
    -0.08
    uta
    -0.08
    ãģĮãĤī
    -0.08
    اØŃ
    -0.08
     oneself
    -0.08
    æ§Ń
    -0.08
     swath
    -0.08
    POSITIVE LOGITS
    请æĤ¨
    0.09
    请çĤ¹åĩ»
    0.09
     Arist
    0.09
    è°ģèĥ½
    0.09
     bitte
    0.09
     please
    0.09
    æ¶ī
    0.09
    åĽ°æī°
    0.09
    åIJŀ
    0.09
    å¼Ĥ
    0.09
    Activations Density 0.091%

    No Known Activations