© 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. 48298
    Prev
    Next
    INDEX
    Explanations

    talking or talked about

    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
    ä¿Ł
    -0.09
    åħ³éŨ
    -0.09
    ä¸Ģçľ¼
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    ç¾Ĭæ¯Ľ
    -0.08
    åĨĻçĿĢ
    -0.08
    åįıåĬŀ
    -0.08
    orthand
    -0.08
    onna
    -0.08
    象
    -0.08
    POSITIVE LOGITS
     talk
    0.13
     Talk
    0.12
    -talk
    0.12
    talk
    0.12
     Talking
    0.10
     about
    0.10
    Talk
    0.10
    è°Ī论
    0.09
    patterns
    0.09
     talked
    0.09
    Activations Density 0.087%

    No Known Activations