© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37442
    Prev
    Next
    INDEX
    Explanations

    population and populations

    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
    orris
    -0.11
    desk
    -0.09
    浸泡
    -0.08
    ä¸Ģä¸Ģ
    -0.08
    ë§ī
    -0.08
     подпиÑģ
    -0.08
     Friend
    -0.08
    宿
    -0.08
    lk
    -0.08
    stro
    -0.08
    POSITIVE LOGITS
    人åı£
    0.13
     populations
    0.12
     population
    0.12
    population
    0.12
    à¸ĵ
    0.12
     наÑģелениÑı
    0.11
    è§Ħ模
    0.11
     quần
    0.10
    åħ´æĹº
    0.10
    Population
    0.10
    Activations Density 0.091%

    No Known Activations