© 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. 27264
    Prev
    Next
    INDEX
    Explanations

    left, answered, away, delivered, 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
     Tonight
    -0.08
    çĶŁãģį
    -0.08
    å¦Ĥæŀľä¸į
    -0.08
    æѤåĪ»
    -0.08
    nor
    -0.07
    eref
    -0.07
    æŃī
    -0.07
    ãģĵãĤĮãģĭãĤī
    -0.07
    erde
    -0.07
    ael
    -0.07
    POSITIVE LOGITS
    è§īå¾Ĺå¾Ī
    0.11
    æĥ³èµ·äºĨ
    0.11
    çľĭäºĨçľĭ
    0.10
    æĥ³èµ·
    0.09
    éļIJ身
    0.09
    æĥ³èµ·æĿ¥
    0.09
    éĻ·åħ¥äºĨ
    0.09
    对æĪij说
    0.09
    äºĨä¸Ģä¼ļåĦ¿
    0.09
    æĥ³äºĨæĥ³
    0.09
    Activations Density 0.040%

    No Known Activations