© 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. 57022
    Prev
    Next
    INDEX
    Explanations

    reaching an audience

    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
     Huff
    -0.10
    лем
    -0.09
    meld
    -0.09
    ä¸İåIJ¦
    -0.09
     Clown
    -0.09
    ë©ĺ
    -0.09
    å¸ĥ
    -0.08
     гÑĢ
    -0.08
     phé
    -0.08
     bande
    -0.08
    POSITIVE LOGITS
     audiences
    0.17
     audience
    0.17
    è§Ĥä¼Ĺ
    0.15
    åıĹä¼Ĺ
    0.14
     Audience
    0.13
    åIJ¬ä¼Ĺ
    0.11
    éĴİ
    0.09
    人群
    0.09
    aud
    0.09
    åŁŁ
    0.08
    Activations Density 0.042%

    No Known Activations