© 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. 2792
    Prev
    Next
    INDEX
    Explanations

    degrading condescension intellectuals fools hand-outs

    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
    /misc
    -0.09
    éĻĨ
    -0.09
     ost
    -0.08
    两家
    -0.08
    bench
    -0.08
    _blocking
    -0.08
     critic
    -0.08
    ãĤ°
    -0.08
    è¢Ĵ
    -0.08
     bench
    -0.08
    POSITIVE LOGITS
    åijĬçŁ¥
    0.10
    èIJ½åIJİ
    0.10
    atives
    0.09
    è¢«åĽ°
    0.09
    åĺı
    0.09
    主åĬ¨æĢ§
    0.08
    è¥ģ
    0.08
    -Headers
    0.08
    æķijæĬ¤
    0.08
    hel
    0.08
    Activations Density 0.020%

    No Known Activations