© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51818
    Prev
    Next
    INDEX
    Explanations

    developer resources

    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
     Benton
    -0.09
    èķĻ
    -0.09
    arena
    -0.09
    æŃ¦åĬŁ
    -0.08
    åĽºåĮĸ
    -0.08
     ë°©
    -0.08
     Din
    -0.08
    ÑĢÑıд
    -0.08
    fi
    -0.08
    æĺ¯åĽ½åĨħ
    -0.08
    POSITIVE LOGITS
    allon
    0.12
    iteur
    0.10
    .invoke
    0.10
    å¼Ĥ
    0.09
    å¥ĩ
    0.09
    .blank
    0.09
    ("[%
    0.09
     Zub
    0.09
     Griff
    0.09
    esub
    0.09
    Activations Density 0.284%

    No Known Activations