© 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. 3749
    Prev
    Next
    INDEX
    Explanations

    Elle, Uno, Nos, pro

    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
     kiá»ĩn
    -0.09
    lus
    -0.09
    ìį¨
    -0.09
    rone
    -0.09
    ãĥ¼ãĤ
    -0.08
     descent
    -0.08
    edList
    -0.08
    lite
    -0.08
    æĵį
    -0.08
    пеÑĩаÑĤ
    -0.08
    POSITIVE LOGITS
    illion
    0.11
    çĶŁæľº
    0.10
    obook
    0.09
    ย
    0.09
    ational
    0.09
    atically
    0.09
    forth
    0.09
    åĪĨæĺİ
    0.09
    .ObjectId
    0.08
    åĭĥåĭĥ
    0.08
    Activations Density 0.148%

    No Known Activations