© 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. 32807
    Prev
    Next
    INDEX
    Explanations

    german, Germany

    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
    -IS
    -0.09
    èµį
    -0.09
    izards
    -0.09
    ãĥĥãĥĪ
    -0.09
    dam
    -0.08
    reek
    -0.08
    edin
    -0.08
    educt
    -0.08
    Ñıд
    -0.08
    æIJ¬è¿ģ
    -0.08
    POSITIVE LOGITS
    佬
    0.10
    ized
    0.10
    isto
    0.09
    ears
    0.09
    ../../../
    0.09
    alogy
    0.09
    ÑĨ
    0.09
    czy
    0.09
    -speaking
    0.09
     Sachs
    0.09
    Activations Density 0.030%

    No Known Activations