© 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. 54182
    Prev
    Next
    INDEX
    Explanations

    parmesan, boiling, cheese, gummy, pitch

    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
    æİ©çĽĸ
    -0.09
    åħ¨åİ¿
    -0.08
    iler
    -0.08
    亲åĪĩ
    -0.08
    ç¹
    -0.08
    ä¸Ģåı¥
    -0.08
    绫
    -0.08
    Cancelable
    -0.08
    ny
    -0.08
    å°±æĺ¯è¦ģ
    -0.08
    POSITIVE LOGITS
    çĻĸ
    0.08
    ingles
    0.08
    æ¦ķ
    0.08
    以èī²
    0.08
    /or
    0.08
    å³Ĵ
    0.08
    åı¯ä»¥èİ·å¾Ĺ
    0.08
    æĪİ
    0.08
     Malk
    0.08
    ä¼ı
    0.07
    Activations Density 0.054%

    No Known Activations