© 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. 56650
    Prev
    Next
    INDEX
    Explanations

    code prefixes and suffixes

    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
    óc
    -0.09
    åĽŀäºĭ
    -0.09
    oire
    -0.09
    ıc
    -0.08
     Rubin
    -0.08
     Sabha
    -0.08
    èį¤
    -0.08
    寰
    -0.08
    箫
    -0.08
    æ¹ĵ
    -0.08
    POSITIVE LOGITS
    缩å°ı
    0.10
    odash
    0.10
    æ£ķèī²
    0.09
    åİĨ代
    0.09
     Laf
    0.09
    Berry
    0.09
    edList
    0.09
    缩
    0.09
     Yates
    0.08
     inland
    0.08
    Activations Density 0.003%

    No Known Activations