© 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. 36749
    Prev
    Next
    INDEX
    Explanations

    crocodile or alligator

    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
    鸽
    -0.08
    æ´Ĵ
    -0.08
    ahi
    -0.08
     Whe
    -0.08
    est
    -0.08
    ularity
    -0.08
    åºļ
    -0.08
    红éħĴ
    -0.08
     miracles
    -0.08
    ums
    -0.08
    POSITIVE LOGITS
    igator
    0.11
    èľ´
    0.11
    igators
    0.10
     Grip
    0.10
    滩
    0.10
    å¤ĸå©Ĩ
    0.10
    emma
    0.09
    澳大
    0.09
    ible
    0.09
    ë¶Ī
    0.09
    Activations Density 0.007%

    No Known Activations