© 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. 1273
    Prev
    Next
    INDEX
    Explanations

    hydroxy compounds and chemical 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
    æī¼
    -0.10
     prise
    -0.09
    æĪĸå°Ĩ
    -0.09
    Ñħи
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    .Len
    -0.08
    encer
    -0.08
    PRI
    -0.08
     PRI
    -0.08
    éģŃéģĩ
    -0.08
    POSITIVE LOGITS
    桶
    0.09
     lẽ
    0.09
    æ³±
    0.09
    顺
    0.09
    åĵĩ
    0.09
     Legs
    0.08
    éłĨ
    0.08
     LINUX
    0.08
    ä¿ļ
    0.08
    -clean
    0.08
    Activations Density 0.173%

    No Known Activations