© 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. 6673
    Prev
    Next
    INDEX
    Explanations

    typical + noun describing a specific case

    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
    .IMAGE
    -0.09
    ä¸ĢåĪĢ
    -0.09
    åīįç½®
    -0.09
    è´°
    -0.09
    issor
    -0.08
    没æĥ³åĪ°
    -0.08
    没æľīæĥ³åĪ°
    -0.08
     bar
    -0.08
    ven
    -0.08
    çļĦå¢ŀéķ¿
    -0.08
    POSITIVE LOGITS
    åħ¸åŀĭ
    0.18
    åħ¸åŀĭçļĦ
    0.16
     typical
    0.16
     Typical
    0.13
    typ
    0.12
     tÃŃ
    0.12
    åı¯èĥ½åĩºçİ°
    0.11
     Äijiá»ĥn
    0.11
    大èĩ´
    0.11
    typename
    0.10
    Activations Density 0.201%

    No Known Activations