© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    church

    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
    èħĬ
    -0.11
    éŁ¿
    -0.11
    åĵį
    -0.10
    éĵł
    -0.10
    æĢ»ç®Ĺ
    -0.10
    çľģæķĻèĤ²åİħ
    -0.10
    è¾Ľèĭ¦
    -0.09
    xit
    -0.09
    ä¼ĺåĬ¿
    -0.09
    ä¸įå¿į
    -0.09
    POSITIVE LOGITS
     woo
    0.09
    èģļä¼ļ
    0.09
    æĪIJ交
    0.08
    pll
    0.08
    æķij
    0.08
    ä¸ĩ家
    0.08
    çļĦæľĢ大
    0.08
    æݥ触
    0.08
    æĬĺ
    0.08
     attraction
    0.08
    Activations Density 0.104%

    No Known Activations