© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9197
    Prev
    Next
    INDEX
    Explanations

    free, no cost

    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
    缩å°ı
    -0.11
    allas
    -0.10
    å¾ĹæĦı
    -0.10
    å¥Ħ
    -0.10
    æĹ©çĤ¹
    -0.10
    ouro
    -0.09
    æĸ°åĮº
    -0.09
    è¿ĻæĿ¡
    -0.09
    çĮĬ
    -0.09
    楫
    -0.09
    POSITIVE LOGITS
    è§Ĥ
    0.08
     Barack
    0.08
    lez
    0.07
    å··
    0.07
    >_
    0.07
    æĬµ
    0.07
    éļ¾æ°ij
    0.07
    tle
    0.07
     Parker
    0.07
    åŃĶ
    0.07
    Activations Density 0.055%

    No Known Activations