© 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. 53203
    Prev
    Next
    INDEX
    Explanations

    360 degrees

    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
    imary
    -0.10
    Mahon
    -0.10
    æĴ°
    -0.10
    佬
    -0.10
    æĪijæĬĬ
    -0.10
    å°Ŀ
    -0.09
    ASTER
    -0.09
    gué
    -0.09
    æ¼±
    -0.09
    amel
    -0.09
    POSITIVE LOGITS
    5
    0.10
    4
    0.09
    7
    0.09
    1
    0.09
    0
    0.09
    2
    0.09
    å¼ıçļĦ
    0.09
    3
    0.09
    ä¸į解
    0.09
    6
    0.08
    Activations Density 0.023%

    No Known Activations