© 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. 18039
    Prev
    Next
    INDEX
    Explanations

    for [organization/entity name]

    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
     interceptor
    -0.08
    SOR
    -0.08
    æĬ¥åĪĬ
    -0.08
    ä¸ī大
    -0.08
    town
    -0.08
     tower
    -0.08
    æIJIJ
    -0.08
    رة
    -0.08
    ailability
    -0.08
    izzo
    -0.08
    POSITIVE LOGITS
    ä¸Ģä¼ļ
    0.10
     priv
    0.10
    رÙĬا
    0.09
     lik
    0.09
    vertise
    0.08
    åĢ¾
    0.08
    جاÙĨ
    0.08
    åĸľ
    0.08
    å§Ķå±Ī
    0.08
    空
    0.08
    Activations Density 0.105%

    No Known Activations