© 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. 9728
    Prev
    Next
    INDEX
    Explanations

    names like Bobby, Joey, or ending in obi/io

    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
    ings
    -0.10
    .linkedin
    -0.10
    ling
    -0.10
    -0.09
    eners
    -0.09
    ner
    -0.09
    heck
    -0.09
    æ¯Ķäºļ
    -0.09
     пÑĥнк
    -0.09
    ãģĹãģ£ãģĭãĤĬãģ¨
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    atura
    0.10
    tain
    0.10
    leanup
    0.09
    UTOR
    0.09
     luck
    0.09
    enzie
    0.09
    fffffff
    0.09
    atical
    0.08
    ×ķ×ĺ
    0.08
    Activations Density 0.007%

    No Known Activations