© 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. 19095
    Prev
    Next
    INDEX
    Explanations

    new additions and creations

    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
    mers
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
    /ajax
    -0.08
    loo
    -0.08
    prm
    -0.08
    ç²ķ
    -0.08
    ilk
    -0.08
    hurst
    -0.08
    itr
    -0.08
    chu
    -0.08
    POSITIVE LOGITS
    æĸ°çļĦ
    0.15
    æĸ°å¢ŀ
    0.15
     new
    0.14
     новÑĭÑħ
    0.13
     новÑĭе
    0.13
    æĸ°äºº
    0.12
    å¢ŀéĩı
    0.12
     nuevas
    0.12
    åĬłçĽŁ
    0.12
    æĸ°åĬł
    0.12
    Activations Density 0.190%

    No Known Activations