© 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. 49686
    Prev
    Next
    INDEX
    Explanations

    document things or information

    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
    fully
    -0.09
    (resourceName
    -0.08
    poke
    -0.08
    æĬ¤æłı
    -0.08
    conomics
    -0.08
    umerator
    -0.08
     dint
    -0.08
    mana
    -0.08
    çľ¼çķĮ
    -0.08
    atty
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.11
    åĴĮæĶ¯æĮģ
    0.10
    äºĨæĪijçļĦ
    0.10
    潦
    0.10
    å°ıäºĭ
    0.10
    оÑī
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    æű
    0.09
    APON
    0.09
    IRD
    0.09
    Activations Density 0.044%

    No Known Activations