© 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. 38587
    Prev
    Next
    INDEX
    Explanations

    names ending in -a or -ra

    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
    ÑĥÑĤÑĮ
    -0.10
    èĽ®
    -0.10
    uring
    -0.09
    iness
    -0.09
    è¯Ŀ说
    -0.09
    诲
    -0.09
    odes
    -0.08
    渤海
    -0.08
    åĬĽäºī
    -0.08
    éĹ¼
    -0.08
    POSITIVE LOGITS
    å§IJ妹
    0.10
    庫
    0.09
    amped
    0.09
    dale
    0.09
    ly
    0.08
    碼
    0.08
    \OptionsResolver
    0.08
    ï¸ı
    0.08
    oops
    0.08
    OperationException
    0.08
    Activations Density 0.007%

    No Known Activations