© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10277
    Prev
    Next
    INDEX
    Explanations

    car makes and models

    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
    ottage
    -0.10
    ä¸ĭä¸Ģ代
    -0.09
    鸾
    -0.09
    éĬ®
    -0.09
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    é¦į
    -0.08
    çĪ¹
    -0.08
    管çIJĨä¸Ńå¿ĥ
    -0.08
    Fore
    -0.08
    strt
    -0.08
    POSITIVE LOGITS
    åĿıäºĨ
    0.09
    åģļåĪ°äºĨ
    0.09
    åī¯å±Ģéķ¿
    0.09
    交ç»Ļ
    0.08
    .spy
    0.08
    oret
    0.08
     cũ
    0.08
    æľīä¸ĢçĤ¹
    0.08
    åıªè¦ģæĺ¯
    0.08
     Äijem
    0.08
    Activations Density 0.081%

    No Known Activations