© 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. 4023
    Prev
    Next
    INDEX
    Explanations

    clinical psychology and assessment

    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
    èµĺ
    -0.12
    ä¸Ģç»ı
    -0.11
    æĮ½
    -0.10
    çĮİ
    -0.10
    hound
    -0.10
     Bison
    -0.09
    egis
    -0.09
    rial
    -0.09
    æīĭä¸ĭ
    -0.09
    elters
    -0.09
    POSITIVE LOGITS
    è¸ı
    0.09
    æīĢåľ¨
    0.09
    aland
    0.09
    æĤłæĤł
    0.09
    äºļ
    0.08
    è§Ħå®ļçļĦ
    0.08
    彩票
    0.08
    大åĴĸ
    0.08
     Psych
    0.08
    $mail
    0.08
    Activations Density 0.189%

    No Known Activations