© 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. 55143
    Prev
    Next
    INDEX
    Explanations

    public speaker, sector, editor, policy

    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
    åħ¼é¡¾
    -0.09
    æĢĿ
    -0.09
     paraph
    -0.09
    ῶ
    -0.08
    究
    -0.08
    обÑĢ
    -0.08
    thic
    -0.08
     Bieber
    -0.08
    usher
    -0.08
    æĺ¾
    -0.08
    POSITIVE LOGITS
    Sent
    0.10
    ä»İå°ıå°±
    0.09
    çĶľçĶľ
    0.09
    å¦ŀ
    0.09
    åīĶ
    0.09
    åĬij
    0.08
    utra
    0.08
    å¤ļå±Ĥ次
    0.08
    å§ij
    0.08
    ALSE
    0.08
    Activations Density 0.029%

    No Known Activations