© 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. 36527
    Prev
    Next
    INDEX
    Explanations

    naming conventions and notation

    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
    亢
    -0.08
    ä¸Ļ
    -0.08
    ä¾ĭè¡Į
    -0.08
     quint
    -0.08
    .lin
    -0.08
    lined
    -0.08
    bed
    -0.08
    otr
    -0.08
     Mas
    -0.08
    äºĶ大
    -0.07
    POSITIVE LOGITS
    约å®ļ
    0.12
     conventions
    0.11
    ä¹łæĥ¯
    0.11
    _USED
    0.10
     convention
    0.10
     DÅ©ng
    0.10
    ä¸Ģä¸Ŀ
    0.10
    vig
    0.09
     terms
    0.09
    åıŁ
    0.09
    Activations Density 0.140%

    No Known Activations