© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8571
    Prev
    Next
    INDEX
    Explanations

    upon us

    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
    íģIJ
    -0.10
    ä¸Ĭå®ĺ
    -0.09
    Ń
    -0.09
     ведÑĮ
    -0.09
    วà¸Ļ
    -0.08
    ort
    -0.08
    åŁ
    -0.08
    om
    -0.08
    éĺ´éĺ³
    -0.08
    ãĥ¼ãĥł
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.13
    atively
    0.10
    soever
    0.10
    ments
    0.09
     dụng
    0.09
    å¾ģç¨ĭ
    0.09
    ãģĤãĤĭç¨ĭ度
    0.09
    ment
    0.09
    datable
    0.09
    Ñĩин
    0.09
    Activations Density 0.031%

    No Known Activations