© 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. 8508
    Prev
    Next
    INDEX
    Explanations

    early life and career

    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
    åĵĢ
    -0.08
     кан
    -0.08
    åIJĪ
    -0.08
    ied
    -0.08
    .sb
    -0.08
    ropa
    -0.08
    æĺİæĹ¥
    -0.08
     bumper
    -0.08
    uci
    -0.08
    7
    -0.08
    POSITIVE LOGITS
    éĤ£æ®µ
    0.15
    æĹ¶æľŁ
    0.12
    æĹ¶æľŁçļĦ
    0.11
    åľ¨äº¬
    0.11
    å²ģæľĪ
    0.10
    æŶåħī
    0.10
    ç³Ĺ
    0.10
    å³¥
    0.09
    æĹ©æľŁ
    0.09
    åĤ¨å¤ĩ
    0.09
    Activations Density 0.180%

    No Known Activations