© 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. 62852
    Prev
    Next
    INDEX
    Explanations

    Ward Smith

    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
    thal
    -0.10
    è¹Ĭ
    -0.09
    ÑģÑı
    -0.09
    iness
    -0.09
    ting
    -0.09
    é²·
    -0.08
     vast
    -0.08
    -0.08
    all
    -0.08
    berger
    -0.08
    POSITIVE LOGITS
    ustr
    0.11
    Ùħر
    0.10
    «
    0.10
    unc
    0.10
    parms
    0.10
    aml
    0.10
    undos
    0.09
    好è¿IJ
    0.09
     cáºŃn
    0.09
    estic
    0.09
    Activations Density 0.409%

    No Known Activations