© 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. 18447
    Prev
    Next
    INDEX
    Explanations

    specific or particular

    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
    éī´
    -0.09
    ateurs
    -0.09
    åĨ³èĥľ
    -0.09
    åĿļåĨ³
    -0.09
    Ùģض
    -0.08
    æĪĺæľ¯
    -0.08
    ç§ijå°Ķ
    -0.08
    bies
    -0.08
    æĬĵ
    -0.08
    åĩŃåĢŁçĿĢ
    -0.08
    POSITIVE LOGITS
    ละ
    0.10
     СмоÑĤÑĢ
    0.09
    china
    0.09
     Ñĩа
    0.09
    urai
    0.08
    åĬĽäºī
    0.08
     vess
    0.08
    åħīçݯ
    0.08
    ãģĹãĤĪãģĨ
    0.08
    èĦĸ
    0.08
    Activations Density 0.015%

    No Known Activations