© 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. 39772
    Prev
    Next
    INDEX
    Explanations

    Che followed by specific endings

    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
    edList
    -0.11
     thiá»ĥu
    -0.10
    ned
    -0.10
    iegel
    -0.10
    ional
    -0.10
    -thirds
    -0.09
    ively
    -0.09
    دÙĪ
    -0.09
    ãģĦãĤĭ
    -0.09
    chaft
    -0.08
    POSITIVE LOGITS
    otle
    0.10
    vron
    0.10
     Ùħصدر
    0.09
    vrolet
    0.09
    iores
    0.09
    dom
    0.09
    doll
    0.09
    seys
    0.09
    è±¹
    0.09
    adle
    0.09
    Activations Density 0.027%

    No Known Activations