© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17178
    Prev
    Next
    INDEX
    Explanations

    capacity, availability, spaces

    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
    ÑĪедÑĪ
    -0.10
    ybrid
    -0.09
     Lun
    -0.09
    èĥİ
    -0.08
    astes
    -0.08
    ÑĤен
    -0.08
    åįģ
    -0.08
    èħ´
    -0.08
    apos
    -0.08
    对åħ¶
    -0.08
    POSITIVE LOGITS
    容éĩı
    0.12
    _capacity
    0.12
     capacity
    0.12
    Capacity
    0.11
    å¸Ń
    0.11
     availability
    0.11
     available
    0.11
    capacity
    0.10
     seats
    0.10
     Capacity
    0.10
    Activations Density 0.124%

    No Known Activations