© 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. 20044
    Prev
    Next
    INDEX
    Explanations

    Sam followed by a surname

    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
    ough
    -0.10
    entifier
    -0.09
    bart
    -0.09
    ilig
    -0.09
    ather
    -0.09
    edList
    -0.09
    URE
    -0.09
    EXT
    -0.08
    裳
    -0.08
    اÙħر
    -0.08
    POSITIVE LOGITS
    urai
    0.12
    plings
    0.11
    ways
    0.11
    -sized
    0.11
    -sama
    0.10
    Ä±ÅŁ
    0.10
    alysis
    0.10
    uele
    0.10
    ãĤĪãģĨãģª
    0.10
    ending
    0.10
    Activations Density 0.022%

    No Known Activations