© 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. 57760
    Prev
    Next
    INDEX
    Explanations

    cyclists, modes of transport, trip planning

    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
    åij¨è¾¹
    -0.09
    å³Ļ
    -0.09
     ди
    -0.09
     cũ
    -0.09
    éĢłåŀĭ
    -0.09
    åīĬ
    -0.09
    ä¸Ģ缴
    -0.08
    èľ»
    -0.08
    _ANT
    -0.08
    çļĦä¼ĺåĬ¿
    -0.08
    POSITIVE LOGITS
    åıĭ好
    0.09
    æ¬²æľĽ
    0.09
    çķħ
    0.09
    è¡Ļ
    0.09
    æ£
    0.09
    caf
    0.09
    æĦīå¿«
    0.08
    oust
    0.08
     lanes
    0.08
    áf
    0.08
    Activations Density 0.017%

    No Known Activations