© 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. 12019
    Prev
    Next
    INDEX
    Explanations

    dialing and area codes

    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¸Ģç«Ļ
    -0.10
    综
    -0.09
    éĻ·
    -0.09
    çļĦéĢļçŁ¥
    -0.09
    æĦı大
    -0.09
    妪
    -0.09
    Destroyed
    -0.09
    è¿Ń
    -0.09
    çļ®
    -0.08
    åĪĨè¡Į
    -0.08
    POSITIVE LOGITS
    IDD
    0.08
    çķĮ
    0.08
    æī£éĻ¤
    0.08
    æĭĶ
    0.08
    (extension
    0.08
    计ç®Ĺæľº
    0.08
     Dew
    0.08
    .bulk
    0.08
     Tail
    0.08
    tail
    0.08
    Activations Density 0.111%

    No Known Activations