© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50589
    Prev
    Next
    INDEX
    Explanations

    on the preposition titles

    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
    éĻħ
    -0.08
    oda
    -0.08
    å®ŀéĻħä¸Ĭæĺ¯
    -0.08
    羡
    -0.08
     Fired
    -0.08
    å°Ĩåħ¶
    -0.08
    .inline
    -0.08
    ingo
    -0.08
    娩
    -0.08
    _orient
    -0.08
    POSITIVE LOGITS
    æĽ´å¥½çļĦ
    0.10
    浩
    0.09
    Publication
    0.09
    æѤ
    0.09
    iesen
    0.09
    .echo
    0.09
    çľ¼éĩĮ
    0.09
    æĽ´æ·±
    0.09
    éĨº
    0.08
    endum
    0.08
    Activations Density 0.275%

    No Known Activations