© 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. 3822
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by more verbs

    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
     Gilles
    -0.10
     xtype
    -0.09
    ãģĬãģĭ
    -0.09
    otto
    -0.09
    ä¸Ģ家
    -0.08
    å¯¹ä½ł
    -0.08
    éĩįå¤§é¡¹çĽ®
    -0.08
    羡æħķ
    -0.08
    =-=-=-=-=-=-=-=-
    -0.08
    è¿Ļ家
    -0.08
    POSITIVE LOGITS
    马æĭī
    0.09
    天ä¸ĭ
    0.09
     коÑĤоÑĢÑĥÑİ
    0.09
    cona
    0.08
    æĦı大
    0.08
    ç¾°
    0.08
     Bare
    0.08
    ega
    0.08
    è°ĭ
    0.08
    ç¾Ķ
    0.08
    Activations Density 0.643%

    No Known Activations