© 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. 33709
    Prev
    Next
    INDEX
    Explanations

    but followed by a word

    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
    忤
    -0.09
     Unfortunately
    -0.08
    没æľīå¿ħè¦ģ
    -0.08
    blas
    -0.08
     Feinstein
    -0.08
    .oper
    -0.08
    à¸IJ
    -0.08
    ALSE
    -0.08
     Erick
    -0.08
    cult
    -0.08
    POSITIVE LOGITS
    çŃĶåºĶ
    0.09
    æĢ»çIJĨ
    0.09
    ç´«
    0.09
    æĥ³åĥı
    0.09
    æĪijæĥ³
    0.09
    aning
    0.08
    éĺŁéķ¿
    0.08
    tings
    0.08
    trak
    0.08
    зв
    0.08
    Activations Density 0.061%

    No Known Activations