© 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. 57159
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ä»»ä½ķ人
    -0.09
     LIC
    -0.09
    itti
    -0.09
    /TR
    -0.09
    æĥ¹
    -0.09
    .addAttribute
    -0.09
    :Any
    -0.09
    .AdapterView
    -0.09
    ialis
    -0.09
    untime
    -0.09
    POSITIVE LOGITS
     lur
    0.09
    å¾Īå°ı
    0.08
     MLM
    0.08
    éű
    0.08
    ange
    0.08
    çĩİ
    0.08
    aron
    0.08
    oger
    0.08
     eup
    0.08
    3
    0.07
    Activations Density 0.209%

    No Known Activations