© 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. 8397
    Prev
    Next
    INDEX
    Explanations

    crowd or crowds

    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
    uur
    -0.09
    oment
    -0.09
    iom
    -0.09
    رÙĪÙĨ
    -0.09
    请大家
    -0.09
    ä¸ĢæŃ¥
    -0.08
    ãĥ£
    -0.08
    ctic
    -0.08
    oader
    -0.08
    çī¢åĽº
    -0.08
    POSITIVE LOGITS
    ings
    0.15
    INGS
    0.13
    lier
    0.11
    spell
    0.10
    lectic
    0.10
    ipo
    0.09
    ships
    0.09
    ourced
    0.09
    ä¿Ŀç¨İ
    0.09
    edException
    0.09
    Activations Density 0.011%

    No Known Activations