© 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. 34211
    Prev
    Next
    INDEX
    Explanations

    amplifier or amplification

    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
    liest
    -0.11
    liness
    -0.11
    ovic
    -0.10
    ë§Ŀ
    -0.10
    angle
    -0.10
    itics
    -0.09
    说æĺ¯
    -0.09
    nton
    -0.09
    zelf
    -0.09
    cke
    -0.09
    POSITIVE LOGITS
    éĵĽ
    0.10
     mẽ
    0.09
    æĪijåıĪ
    0.09
    棣
    0.09
    plitude
    0.09
    äºĨ许å¤ļ
    0.09
     дов
    0.08
    forth
    0.08
    浦
    0.08
    ;amp
    0.08
    Activations Density 0.027%

    No Known Activations