© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7408
    Prev
    Next
    INDEX
    Explanations

    radioactive isotopes and labels

    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
    æĢ§åij½
    -0.09
    rende
    -0.08
    宿èĪį
    -0.08
    å¸IJ篷
    -0.08
    æ¯ı个æľĪ
    -0.08
    è¶ĭäºİ
    -0.08
    å¾Īé«ĺåħ´
    -0.08
    å°ijä¸įäºĨ
    -0.08
    æİĴ污
    -0.08
    FER
    -0.08
    POSITIVE LOGITS
    arel
    0.10
    tracker
    0.09
    -labelled
    0.09
    è´¡
    0.09
     isot
    0.09
    onis
    0.09
    æłĩçŃ¾
    0.09
    æłĩè®°
    0.09
     veter
    0.09
    _bm
    0.08
    Activations Density 0.266%

    No Known Activations