© 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. 17246
    Prev
    Next
    INDEX
    Explanations

    email client mail server configuration

    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
    ä»
    -0.09
    ä¸įå¿į
    -0.09
    Ãł
    -0.08
    ä¸įç»ı
    -0.08
    atform
    -0.08
    è·ij
    -0.08
    ä¸ĢçĽ´æ²¡æľī
    -0.08
     commerce
    -0.08
    æĹ©æĹ©
    -0.08
    æı©
    -0.08
    POSITIVE LOGITS
    amma
    0.10
    zend
    0.10
    è¿·
    0.09
    çªģåĩº
    0.09
    anas
    0.09
    axed
    0.09
    _ADAPTER
    0.09
    ijn
    0.09
    íĥĪ
    0.09
    -wsj
    0.09
    Activations Density 0.028%

    No Known Activations