© 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. 58541
    Prev
    Next
    INDEX
    Explanations

    source indicating PTI or official briefing

    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
    amen
    -0.10
    ä¸Ģç«Ļ
    -0.09
    æ··
    -0.08
    ais
    -0.08
    ardo
    -0.08
    çŀ§
    -0.08
    å±ģ
    -0.08
    æĪij没æľī
    -0.08
    æ¿Ģåħī
    -0.08
    çıŀ
    -0.08
    POSITIVE LOGITS
    åİŁä»¶
    0.10
    æ¡·
    0.09
    _FP
    0.09
    reich
    0.09
    uffy
    0.08
    èħĵ
    0.08
    第ä¸Ģ书记
    0.08
    俸
    0.08
    说å®Į
    0.08
    phony
    0.08
    Activations Density 0.011%

    No Known Activations