© 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. 50623
    Prev
    Next
    INDEX
    Explanations

    about time or same age

    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
    æĦıåĽ¾
    -0.09
    ä¿ļ
    -0.09
    åIJ¬è¯¾
    -0.09
    _RM
    -0.09
    æĿ¥åİĨ
    -0.08
    çĹ¹
    -0.08
    èŁł
    -0.08
    arı
    -0.08
    çĤ¹æ»´
    -0.08
    æ¡Į
    -0.08
    POSITIVE LOGITS
    çIJĨæĥ³çļĦ
    0.09
    гаÑĢ
    0.08
     Caul
    0.08
    æ°¸æģĴ
    0.08
    çªĸ
    0.08
    uten
    0.08
    æĩ
    0.08
    uilt
    0.08
    è¹ĩ
    0.08
    sto
    0.08
    Activations Density 0.018%

    No Known Activations