© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37541
    Prev
    Next
    INDEX
    Explanations

    been previously used or damaged

    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
    åıįè¿ĩæĿ¥
    -0.09
    leting
    -0.09
    æĹ¢æľī
    -0.09
    èµ·åĪ°
    -0.08
    leted
    -0.08
    çľĭä¸Ģçľĭ
    -0.08
    ISK
    -0.08
    è°ĥåīĤ
    -0.08
    ç¢į
    -0.08
     Stadium
    -0.08
    POSITIVE LOGITS
    ç»ıåİĨè¿ĩ
    0.11
    çĹķ迹
    0.11
    被人
    0.10
    ares
    0.10
    è¿ĩçļĦ
    0.09
    å¾Īä¹ħ
    0.09
    åıĪ被
    0.09
    æĹłæķ°æ¬¡
    0.09
    åİ»è¿ĩ
    0.09
    å¤ļ次
    0.09
    Activations Density 0.114%

    No Known Activations