© 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. 1718
    Prev
    Next
    INDEX
    Explanations

    takes on

    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
    анг
    -0.10
    Ñħод
    -0.09
    AccessType
    -0.09
    /un
    -0.08
    çħİ
    -0.08
    /english
    -0.08
    äºĮç»´
    -0.08
    -maker
    -0.08
    å¦ĤæĦı
    -0.08
    way
    -0.08
    POSITIVE LOGITS
    åħ³éĶ®æĺ¯
    0.10
    åĢĴæĺ¯
    0.09
    ledo
    0.09
    æĦ
    0.09
    çĺª
    0.09
     Hampton
    0.09
    ä¸ĸçķĮ级
    0.09
    è¾į
    0.08
    ä¸ĸçķĮä¸Ģæµģ
    0.08
    igua
    0.08
    Activations Density 0.004%

    No Known Activations