© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51553
    Prev
    Next
    INDEX
    Explanations

    advertisement call

    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
    å¿«ä¸ī
    -0.09
    è§ģè¯ģ
    -0.08
    社ä¼ļç»Ħç»ĩ
    -0.08
    ä½Ī
    -0.08
    å½ĵæĹ¶çļĦ
    -0.08
    亲æĪļ
    -0.07
    èĩ¾
    -0.07
    ç¶ļ
    -0.07
    è°ı
    -0.07
    ä»Ģä¹Īä¸ľè¥¿
    -0.07
    POSITIVE LOGITS
    管å§Ķä¼ļ
    0.09
    CTYPE
    0.09
    âĿĩ
    0.08
    лен
    0.08
    管çIJĨåĬŀæ³ķ
    0.08
    ictured
    0.08
    chè
    0.08
    BOSE
    0.08
    illion
    0.08
     Hairst
    0.08
    Activations Density 4.052%

    No Known Activations