© 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. 11410
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
     themselves
    -0.10
    å°ıå§ijå¨ĺ
    -0.10
    weet
    -0.09
    å´¤
    -0.09
    åĬ³ç´¯
    -0.09
    éĢĢ款
    -0.09
    çĸ³
    -0.09
    ichel
    -0.09
    ä¸Ģ个个
    -0.09
    åĮħåĽ´
    -0.08
    POSITIVE LOGITS
    .fhir
    0.10
    son
    0.09
    asic
    0.08
    æĭĽ
    0.08
     capitals
    0.08
    phanumeric
    0.08
    IOC
    0.08
    åŁ
    0.08
    daq
    0.08
    hei
    0.08
    Activations Density 0.058%

    No Known Activations