© 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. 9060
    Prev
    Next
    INDEX
    Explanations

    falling asleep or first names

    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
    zin
    -0.10
    çŃ²
    -0.09
    ustin
    -0.09
    åįģå¤ļ
    -0.09
    iest
    -0.09
    NESS
    -0.08
    anst
    -0.08
    .asc
    -0.08
    人士
    -0.08
    夫人
    -0.08
    POSITIVE LOGITS
    åĽº
    0.09
    RAND
    0.08
    éĻĮ
    0.08
    æĥĺ
    0.08
    褶
    0.08
    qua
    0.08
     COPYING
    0.08
    owed
    0.08
    æĭĩ
    0.08
     purported
    0.08
    Activations Density 0.004%

    No Known Activations