© 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. 4413
    Prev
    Next
    INDEX
    Explanations

    informed consent

    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
    åįıä½ľ
    -0.08
    éĥİ
    -0.08
     credibility
    -0.08
    éŀ
    -0.08
    бав
    -0.08
     frustr
    -0.08
    IFIER
    -0.08
    åºĻ
    -0.08
    çĥ¹
    -0.08
     Norman
    -0.07
    POSITIVE LOGITS
     consent
    0.17
    åIJĮæĦı
    0.15
    ä¸įåIJĮæĦı
    0.15
     Consent
    0.14
    çŃ¾ç½²
    0.13
     Ñģог
    0.13
    çŃ¾åŃĹ
    0.12
    çŃ¾åIJį
    0.11
     consenting
    0.11
    çŃ¾ç½²äºĨ
    0.11
    Activations Density 0.104%

    No Known Activations