© 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. 23936
    Prev
    Next
    INDEX
    Explanations

    full service

    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
    ConnectionString
    -0.09
    æľĹ
    -0.09
    MR
    -0.08
    çľĭå¾Ĺ
    -0.08
    ennes
    -0.08
    hub
    -0.08
    lc
    -0.08
     fy
    -0.08
    asad
    -0.08
    lymp
    -0.08
    POSITIVE LOGITS
    é«Ń
    0.09
    示
    0.09
    slug
    0.09
    èĥĮåıĽ
    0.09
    xin
    0.08
    æ¸ħæĺİ
    0.08
    é£İåij³
    0.08
    agra
    0.08
     slug
    0.08
    çĶ¨èį¯
    0.08
    Activations Density 0.145%

    No Known Activations