© 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. 35653
    Prev
    Next
    INDEX
    Explanations

    Brown

    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
    åŃª
    -0.10
    车åĨħ
    -0.10
    ableObject
    -0.10
    unami
    -0.10
    CALE
    -0.09
    rosse
    -0.09
    plers
    -0.09
     UIF
    -0.09
    acle
    -0.09
    ToBounds
    -0.09
    POSITIVE LOGITS
    ont
    0.09
     Ramsey
    0.09
    év
    0.09
    å®ģåİ¿
    0.08
     cose
    0.08
    å®ģ
    0.08
    åĪĩæį¢
    0.08
     Kou
    0.08
    sin
    0.08
    伺
    0.08
    Activations Density 0.021%

    No Known Activations