© 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. 35401
    Prev
    Next
    INDEX
    Explanations

    DIY projects and homebrew equipment

    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
    åŁ
    -0.11
    flex
    -0.09
    èıĸ
    -0.09
     жиз
    -0.09
    noch
    -0.08
    æļ®
    -0.08
    _digit
    -0.08
    uir
    -0.08
    æ¯Ľä¸»å¸Ń
    -0.08
    çIJĨç§ij
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.11
    ers
    0.10
    ï¸
    0.10
    å¾Ĺå¾Ī
    0.09
    elves
    0.09
     Ñģебе
    0.09
    们éĥ½
    0.09
    äºĽä»Ģä¹Ī
    0.09
    ields
    0.09
     nhiên
    0.09
    Activations Density 0.004%

    No Known Activations