© 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. 22673
    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
    ãģıãĤĮ
    -0.09
    æĪ´
    -0.09
    amar
    -0.09
    ussen
    -0.08
     Soap
    -0.08
    alogy
    -0.07
    pls
    -0.07
    prus
    -0.07
    ãģ£
    -0.07
     Chapters
    -0.07
    POSITIVE LOGITS
    robat
    0.10
    .ud
    0.09
    _Osc
    0.09
    æľ¬äºº
    0.09
    åĪĿè¡·
    0.09
    纯åĩĢ
    0.09
    .uf
    0.09
    ÑĪим
    0.09
    odef
    0.09
    utow
    0.09
    Activations Density 0.000%

    No Known Activations