© 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. 62274
    Prev
    Next
    INDEX
    Explanations

    MD, PhD, OD, PT abbreviations

    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
    åħīå½±
    -0.10
    osto
    -0.09
    steen
    -0.09
    çe
    -0.09
    rens
    -0.09
    stell
    -0.09
    sten
    -0.09
    è®°å¾Ĺ
    -0.09
    ermo
    -0.09
    æĥ®
    -0.09
    POSITIVE LOGITS
    ä¸Ģæŀļ
    0.09
    _UID
    0.08
    cosa
    0.08
    éŨåīį
    0.08
    æı¡ä½ı
    0.08
    åľ¨åĽ½åĨħ
    0.08
    å±Ĥåĩº
    0.08
    å¤Ħåľ¨
    0.08
    æľºåħ³
    0.08
    åĮ¹
    0.08
    Activations Density 0.107%

    No Known Activations