© 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. 23494
    Prev
    Next
    INDEX
    Explanations

    what makes

    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
    æŃ£æĸĩ
    -0.09
    绯
    -0.09
     Claudia
    -0.09
    æݨåĩºçļĦ
    -0.09
    ibo
    -0.08
    aran
    -0.08
    ä¼łåªĴ
    -0.08
     Pitch
    -0.08
    Playback
    -0.08
     latino
    -0.08
    POSITIVE LOGITS
    çŃīçī¹çĤ¹
    0.09
     оÑĤлиÑĩ
    0.08
    å¦ĤæĦı
    0.08
    lesh
    0.08
    æĪijåĽ½
    0.08
    iffe
    0.08
     Traits
    0.08
     Fulton
    0.08
    æľ¬æĬ¥
    0.08
    é¦ģ
    0.08
    Activations Density 0.019%

    No Known Activations