© 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. 3457
    Prev
    Next
    INDEX
    Explanations

    PDA

    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
    æĹ©æĻļ
    -0.09
     ve
    -0.09
    åIJ¸åıĸ
    -0.09
    èĨº
    -0.08
     tread
    -0.08
    ä»»ä½ķ人
    -0.08
    好åĿı
    -0.08
     unl
    -0.08
    äºĶå®ĺ
    -0.08
    STDOUT
    -0.08
    POSITIVE LOGITS
    ini
    0.09
     Personal
    0.09
    åģ¶
    0.09
    ç»ħ
    0.09
    å°º
    0.08
    .Dot
    0.08
    åħħçĶµ
    0.08
    åįģåĽĽäºĶ
    0.08
    urf
    0.08
    ocket
    0.08
    Activations Density 0.081%

    No Known Activations