© 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. 8630
    Prev
    Next
    INDEX
    Explanations

    copies of documentation or materials

    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
    ibia
    -0.09
    rox
    -0.08
    оÑĩек
    -0.08
    ÑģÑĤе
    -0.08
    æĿ¾
    -0.08
    对äºİæĪij们
    -0.08
    chap
    -0.08
    MDB
    -0.08
     Chandler
    -0.08
    å¹´åĪĿ
    -0.08
    POSITIVE LOGITS
    .putString
    0.09
    èĤļåŃIJ
    0.09
    ä¼ģä¸ļ管çIJĨ
    0.09
    亲åıĭ
    0.08
    åĩ³
    0.08
    lop
    0.08
    æIJľç´¢å¼ķæĵİ
    0.08
    ordes
    0.08
    0
    0.08
    æĥħ
    0.08
    Activations Density 0.168%

    No Known Activations