© 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. 17944
    Prev
    Next
    INDEX
    Explanations

    knowledge base

    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
    ter
    -0.10
    åĨµ
    -0.10
    sWith
    -0.09
    工夫
    -0.09
    æĪijæĬĬ
    -0.09
    que
    -0.08
    urr
    -0.08
    éĢĤéĩı
    -0.08
    åŃIJéĩĮ
    -0.08
    ä¸ĸçķĮè§Ĥ
    -0.08
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.10
    产æĿĥ
    0.10
    对åѦçĶŁ
    0.09
    _FACTORY
    0.09
    åłĤ
    0.09
    çĹŀ
    0.09
     кли
    0.08
    aupt
    0.08
    人士
    0.08
    _BUFF
    0.08
    Activations Density 0.024%

    No Known Activations