© 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. 51867
    Prev
    Next
    INDEX
    Explanations

    run into trouble

    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
    è¿ĺä¸įå¤Ł
    -0.10
     اÙĦÙĨÙĤ
    -0.10
    å·¥ä½ľå²Ĺä½į
    -0.10
    èİł
    -0.10
    еÑī
    -0.10
    ç«£
    -0.09
    è¾ľè´Ł
    -0.09
    _checked
    -0.08
     impressions
    -0.08
    _completed
    -0.08
    POSITIVE LOGITS
    éģĩåĪ°äºĨ
    0.17
    碰åĪ°
    0.15
    æĮ«æĬĺ
    0.13
    éģĩåĪ°
    0.13
    éģĩä¸Ĭ
    0.12
    éļľç¢į
    0.12
    åıĹåĪ°äºĨ
    0.12
    éģŃéģĩ
    0.12
    éģŃåĪ°
    0.11
    éģŃ
    0.10
    Activations Density 0.114%

    No Known Activations