© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10102
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    soever
    -0.10
    ronic
    -0.09
    eenth
    -0.09
    wards
    -0.08
    åĬ±
    -0.08
    noon
    -0.08
    ourg
    -0.08
    grave
    -0.08
     Jennings
    -0.08
    CreateDate
    -0.08
    POSITIVE LOGITS
    ity
    0.15
    å°ıäºĭ
    0.13
    izes
    0.12
    ly
    0.12
    ities
    0.11
     amounts
    0.11
    izing
    0.11
    çIJIJ
    0.11
    ized
    0.10
    mente
    0.10
    Activations Density 0.019%

    No Known Activations