© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52341
    Prev
    Next
    INDEX
    Explanations

    Version or Inc

    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
    ...↵
    -0.14
    ...,
    -0.12
    ep
    -0.12
    âĢ¦
    -0.12
    ...
    -0.11
    ...)
    -0.11
    the
    -0.10
    ...↵↵
    -0.10
    &#
    -0.10
    pping
    -0.10
    POSITIVE LOGITS
    å°¤åħ¶æĺ¯
    0.17
    çī¹åĪ«æĺ¯
    0.16
    å°¤åħ¶æĺ¯åľ¨
    0.14
    以åıĬ
    0.14
    ä¸Ķ
    0.13
     especially
    0.13
    çī¹åĪ«æĺ¯åľ¨
    0.12
    ãģĤãĤĭãģĦãģ¯
    0.12
    çĶļèĩ³æĺ¯
    0.12
    etheless
    0.12
    Activations Density 3.446%

    No Known Activations