© 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. 1418
    Prev
    Next
    INDEX
    Explanations

    Rutgers University or Routledge

    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
    venue
    -0.10
    hip
    -0.10
    çħ¨
    -0.10
    ãĤıãĤĬ
    -0.10
    éľĦ
    -0.09
    èijŃ
    -0.09
    ÑįÑĤомÑĥ
    -0.09
    寤
    -0.09
    orth
    -0.09
    iller
    -0.09
    POSITIVE LOGITS
    åĬ²
    0.10
    çī¹éķ¿
    0.08
    ctor
    0.08
    åĸĺ
    0.08
    ech
    0.08
    Ñı
    0.08
    å®ŀçī©
    0.08
    tur
    0.08
     kot
    0.08
    ä¾Ī
    0.07
    Activations Density 0.002%

    No Known Activations