© 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. 36602
    Prev
    Next
    INDEX
    Explanations

    words followed by descriptive words

    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
    erus
    -0.09
    /loader
    -0.09
    vÃŃ
    -0.08
    æīĪ
    -0.08
    éĥ½æĥ³
    -0.08
    kn
    -0.08
    éĦ£
    -0.08
    ê°Ŀ
    -0.08
    å¯ĵ
    -0.08
    .mx
    -0.08
    POSITIVE LOGITS
    mith
    0.13
    èĪħ
    0.09
    worth
    0.09
    æ¾ľ
    0.09
    Ñĩин
    0.09
    wort
    0.08
     words
    0.08
    manship
    0.08
    èĽ°
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    Activations Density 0.016%

    No Known Activations