© 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. 55820
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    geries
    -0.12
    åģļçļĦäºĭæĥħ
    -0.11
    沸èħ¾
    -0.11
    æīĢæıIJä¾ĽçļĦ
    -0.10
    俱
    -0.10
    奢åįİ
    -0.10
    è¹ĭ
    -0.10
    ä¾Ī
    -0.10
     ÐĵоÑĢ
    -0.09
    åĹŁ
    -0.09
    POSITIVE LOGITS
     led
    0.08
    god
    0.08
    嫦
    0.07
    eter
    0.07
     Led
    0.07
     Gloss
    0.07
    ноп
    0.07
     cram
    0.07
    Kernel
    0.07
    esian
    0.07
    Activations Density 0.209%

    No Known Activations